ComfyUI version 0.3.63

* Update template to 0.1.92

* Update template to 0.1.93

.ci/windows_amd_base_files/README_VERY_IMPORTANT.txt

@@ -0,0 +1,27 @@
+As of the time of writing this you need this preview driver for best results:
+https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-PREVIEW.html
+
+HOW TO RUN:
+
+If you have a AMD gpu:
+
+run_amd_gpu.bat
+
+If you have memory issues you can try disabling the smart memory management by running comfyui with:
+
+run_amd_gpu_disable_smart_memory.bat
+
+IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints
+
+You can download the stable diffusion XL one from: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors
+
+
+RECOMMENDED WAY TO UPDATE:
+To update the ComfyUI code: update\update_comfyui.bat
+
+
+TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
+In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
+Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.
+
+

.ci/windows_amd_base_files/run_amd_gpu_disable_smart_memory.bat

@@ -0,0 +1,2 @@
+.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --disable-smart-memory
+pause

.ci/windows_nvidia_base_files/run_nvidia_gpu.bat

@@ -0,0 +1,2 @@
+.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
+pause

.github/workflows/release-stable-all.yml

@@ -0,0 +1,61 @@
+name: "Release Stable All Portable Versions"
+
+on:
+  workflow_dispatch:
+    inputs:
+      git_tag:
+        description: 'Git tag'
+        required: true
+        type: string
+
+jobs:
+  release_nvidia_default:
+    permissions:
+      contents: "write"
+      packages: "write"
+      pull-requests: "read"
+    name: "Release NVIDIA Default (cu129)"
+    uses: ./.github/workflows/stable-release.yml
+    with:
+      git_tag: ${{ inputs.git_tag }}
+      cache_tag: "cu129"
+      python_minor: "13"
+      python_patch: "6"
+      rel_name: "nvidia"
+      rel_extra_name: ""
+      test_release: true
+    secrets: inherit
+
+  release_nvidia_cu128:
+    permissions:
+      contents: "write"
+      packages: "write"
+      pull-requests: "read"
+    name: "Release NVIDIA cu128"
+    uses: ./.github/workflows/stable-release.yml
+    with:
+      git_tag: ${{ inputs.git_tag }}
+      cache_tag: "cu128"
+      python_minor: "12"
+      python_patch: "10"
+      rel_name: "nvidia"
+      rel_extra_name: "_cu128"
+      test_release: true
+    secrets: inherit
+
+  release_amd_rocm:
+    permissions:
+      contents: "write"
+      packages: "write"
+      pull-requests: "read"
+    name: "Release AMD ROCm 6.4.4"
+    uses: ./.github/workflows/stable-release.yml
+    with:
+      git_tag: ${{ inputs.git_tag }}
+      cache_tag: "rocm644"
+      python_minor: "12"
+      python_patch: "10"
+      rel_name: "amd"
+      rel_extra_name: ""
+      test_release: false
+    secrets: inherit

.github/workflows/ruff.yml

@@ -21,3 +21,28 @@ jobs:
 
     - name: Run Ruff
       run: ruff check .
+
+  pylint:
+    name: Run Pylint
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install requirements
+      run: |
+        python -m pip install --upgrade pip
+        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        pip install -r requirements.txt
+
+    - name: Install Pylint
+      run: pip install pylint
+
+    - name: Run Pylint
+      run: pylint comfy_api_nodes

.github/workflows/stable-release.yml

@@ -2,17 +2,17 @@
 name: "Release Stable Version"
 
 on:
-  workflow_dispatch:
+  workflow_call:
     inputs:
       git_tag:
         description: 'Git tag'
         required: true
         type: string
-      cu:
-        description: 'CUDA version'
+      cache_tag:
+        description: 'Cached dependencies tag'
         required: true
         type: string
-        default: "129"
+        default: "cu129"
       python_minor:
         description: 'Python minor version'
         required: true
@@ -23,7 +23,57 @@ on:
         required: true
         type: string
         default: "6"
-
+      rel_name:
+        description: 'Release name'
+        required: true
+        type: string
+        default: "nvidia"
+      rel_extra_name:
+        description: 'Release extra name'
+        required: false
+        type: string
+        default: ""
+      test_release:
+        description: 'Test Release'
+        required: true
+        type: boolean
+        default: true
+  workflow_dispatch:
+    inputs:
+      git_tag:
+        description: 'Git tag'
+        required: true
+        type: string
+      cache_tag:
+        description: 'Cached dependencies tag'
+        required: true
+        type: string
+        default: "cu129"
+      python_minor:
+        description: 'Python minor version'
+        required: true
+        type: string
+        default: "13"
+      python_patch:
+        description: 'Python patch version'
+        required: true
+        type: string
+        default: "6"
+      rel_name:
+        description: 'Release name'
+        required: true
+        type: string
+        default: "nvidia"
+      rel_extra_name:
+        description: 'Release extra name'
+        required: false
+        type: string
+        default: ""
+      test_release:
+        description: 'Test Release'
+        required: true
+        type: boolean
+        default: true
 
 jobs:
   package_comfy_windows:
@@ -42,15 +92,15 @@ jobs:
         id: cache
         with:
           path: |
-            cu${{ inputs.cu }}_python_deps.tar
+            ${{ inputs.cache_tag }}_python_deps.tar
             update_comfyui_and_python_dependencies.bat
-          key: ${{ runner.os }}-build-cu${{ inputs.cu }}-${{ inputs.python_minor }}
+          key: ${{ runner.os }}-build-${{ inputs.cache_tag }}-${{ inputs.python_minor }}
       - shell: bash
         run: |
-          mv cu${{ inputs.cu }}_python_deps.tar ../
+          mv ${{ inputs.cache_tag }}_python_deps.tar ../
           mv update_comfyui_and_python_dependencies.bat ../
           cd ..
-          tar xf cu${{ inputs.cu }}_python_deps.tar
+          tar xf ${{ inputs.cache_tag }}_python_deps.tar
           pwd
           ls
 
@@ -65,12 +115,19 @@ jobs:
           echo 'import site' >> ./python3${{ inputs.python_minor }}._pth
           curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
           ./python.exe get-pip.py
-          ./python.exe -s -m pip install ../cu${{ inputs.cu }}_python_deps/*
+          ./python.exe -s -m pip install ../${{ inputs.cache_tag }}_python_deps/*
+
+          grep comfyui ../ComfyUI/requirements.txt > ./requirements_comfyui.txt
+          ./python.exe -s -m pip install -r requirements_comfyui.txt
+          rm requirements_comfyui.txt
+
           sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
 
-          rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
-          rm ./Lib/site-packages/torch/lib/libprotoc.lib
-          rm ./Lib/site-packages/torch/lib/libprotobuf.lib
+          if test -f ./Lib/site-packages/torch/lib/dnnl.lib; then
+            rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
+            rm ./Lib/site-packages/torch/lib/libprotoc.lib
+            rm ./Lib/site-packages/torch/lib/libprotobuf.lib
+          fi
 
           cd ..
 
@@ -85,14 +142,18 @@ jobs:
 
           mkdir update
           cp -r ComfyUI/.ci/update_windows/* ./update/
-          cp -r ComfyUI/.ci/windows_base_files/* ./
+          cp -r ComfyUI/.ci/windows_${{ inputs.rel_name }}_base_files/* ./
           cp ../update_comfyui_and_python_dependencies.bat ./update/
 
           cd ..
 
           "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 ComfyUI_windows_portable.7z ComfyUI_windows_portable
-          mv ComfyUI_windows_portable.7z ComfyUI/ComfyUI_windows_portable_nvidia.7z
+          mv ComfyUI_windows_portable.7z ComfyUI/ComfyUI_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z
 
+      - shell: bash
+        if: ${{ inputs.test_release }}
+        run: |
+          cd ..
           cd ComfyUI_windows_portable
           python_embeded/python.exe -s ComfyUI/main.py --quick-test-for-ci --cpu
 
@@ -101,10 +162,9 @@ jobs:
           ls
 
       - name: Upload binaries to release
-        uses: svenstaro/upload-release-action@v2
+        uses: softprops/action-gh-release@v2
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: ComfyUI_windows_portable_nvidia.7z
-          tag: ${{ inputs.git_tag }}
-          overwrite: true
+          files: ComfyUI_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z
+          tag_name: ${{ inputs.git_tag }}
           draft: true
+          overwrite_files: true

.github/workflows/test-unit.yml

@@ -10,7 +10,7 @@ jobs:
   test:
     strategy:
       matrix:
-        os: [ubuntu-latest, windows-latest, macos-latest]
+        os: [ubuntu-latest, windows-2022, macos-latest]
     runs-on: ${{ matrix.os }}
     continue-on-error: true
     steps:

.github/workflows/windows_release_dependencies.yml

@@ -56,7 +56,8 @@ jobs:
             ..\python_embeded\python.exe -s -m pip install --upgrade torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r ../ComfyUI/requirements.txt pygit2
             pause" > update_comfyui_and_python_dependencies.bat
 
-            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} ${{ inputs.extra_dependencies }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r requirements.txt pygit2 -w ./temp_wheel_dir
+            grep -v comfyui requirements.txt > requirements_nocomfyui.txt
+            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} ${{ inputs.extra_dependencies }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r requirements_nocomfyui.txt pygit2 -w ./temp_wheel_dir
             python -m pip install --no-cache-dir ./temp_wheel_dir/*
             echo installed basic
             ls -lah temp_wheel_dir

.github/workflows/windows_release_dependencies_manual.yml

@@ -0,0 +1,64 @@
+name: "Windows Release dependencies Manual"
+
+on:
+  workflow_dispatch:
+    inputs:
+      torch_dependencies:
+        description: 'torch dependencies'
+        required: false
+        type: string
+        default: "torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu128"
+      cache_tag:
+        description: 'Cached dependencies tag'
+        required: true
+        type: string
+        default: "cu128"
+
+      python_minor:
+        description: 'python minor version'
+        required: true
+        type: string
+        default: "12"
+
+      python_patch:
+        description: 'python patch version'
+        required: true
+        type: string
+        default: "10"
+
+jobs:
+  build_dependencies:
+    runs-on: windows-latest
+    steps:
+        - uses: actions/checkout@v4
+        - uses: actions/setup-python@v5
+          with:
+            python-version: 3.${{ inputs.python_minor }}.${{ inputs.python_patch }}
+
+        - shell: bash
+          run: |
+            echo "@echo off
+            call update_comfyui.bat nopause
+            echo -
+            echo This will try to update pytorch and all python dependencies.
+            echo -
+            echo If you just want to update normally, close this and run update_comfyui.bat instead.
+            echo -
+            pause
+            ..\python_embeded\python.exe -s -m pip install --upgrade ${{ inputs.torch_dependencies }} -r ../ComfyUI/requirements.txt pygit2
+            pause" > update_comfyui_and_python_dependencies.bat
+
+            grep -v comfyui requirements.txt > requirements_nocomfyui.txt
+            python -m pip wheel --no-cache-dir ${{ inputs.torch_dependencies }} -r requirements_nocomfyui.txt pygit2 -w ./temp_wheel_dir
+            python -m pip install --no-cache-dir ./temp_wheel_dir/*
+            echo installed basic
+            ls -lah temp_wheel_dir
+            mv temp_wheel_dir ${{ inputs.cache_tag }}_python_deps
+            tar cf ${{ inputs.cache_tag }}_python_deps.tar ${{ inputs.cache_tag }}_python_deps
+
+        - uses: actions/cache/save@v4
+          with:
+            path: |
+              ${{ inputs.cache_tag }}_python_deps.tar
+              update_comfyui_and_python_dependencies.bat
+            key: ${{ runner.os }}-build-${{ inputs.cache_tag }}-${{ inputs.python_minor }}

.github/workflows/windows_release_nightly_pytorch.yml

@@ -68,7 +68,7 @@ jobs:
 
             mkdir update
             cp -r ComfyUI/.ci/update_windows/* ./update/
-            cp -r ComfyUI/.ci/windows_base_files/* ./
+            cp -r ComfyUI/.ci/windows_nvidia_base_files/* ./
             cp -r ComfyUI/.ci/windows_nightly_base_files/* ./
 
             echo "call update_comfyui.bat nopause

.github/workflows/windows_release_package.yml

@@ -81,7 +81,7 @@ jobs:
 
             mkdir update
             cp -r ComfyUI/.ci/update_windows/* ./update/
-            cp -r ComfyUI/.ci/windows_base_files/* ./
+            cp -r ComfyUI/.ci/windows_nvidia_base_files/* ./
             cp ../update_comfyui_and_python_dependencies.bat ./update/
 
             cd ..

CODEOWNERS

@@ -1,25 +1,3 @@
 # Admins
 * @comfyanonymous
-
-# Note: Github teams syntax cannot be used here as the repo is not owned by Comfy-Org.
-# Inlined the team members for now.
-
-# Maintainers
-*.md @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/tests/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/tests-unit/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/notebooks/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/script_examples/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/.github/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/requirements.txt @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-/pyproject.toml @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @Kosinkadink @christian-byrne @guill
-
-# Python web server
-/api_server/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @christian-byrne @guill
-/app/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @christian-byrne @guill
-/utils/ @yoland68 @robinjhuang @webfiltered @pythongosssss @ltdrdata @christian-byrne @guill
-
-# Node developers
-/comfy_extras/ @yoland68 @robinjhuang @pythongosssss @ltdrdata @Kosinkadink @webfiltered @christian-byrne @guill
-/comfy/comfy_types/ @yoland68 @robinjhuang @pythongosssss @ltdrdata @Kosinkadink @webfiltered @christian-byrne @guill
-/comfy_api_nodes/ @yoland68 @robinjhuang @pythongosssss @ltdrdata @Kosinkadink @webfiltered @christian-byrne @guill
+* @kosinkadink

README.md

@@ -176,6 +176,12 @@ Simply download, extract with [7-Zip](https://7-zip.org) and run. Make sure you
 
 If you have trouble extracting it, right click the file -> properties -> unblock
 
+#### Alternative Downloads:
+
+[Experimental portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
+
+[Portable with pytorch cuda 12.8 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu128.7z) (Supports Nvidia 10 series and older GPUs).
+
 #### How do I share models between another UI and ComfyUI?
 
 See the [Config file](extra_model_paths.yaml.example) to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.
@@ -200,14 +206,32 @@ Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints
 Put your VAE in: models/vae
 
 
-### AMD GPUs (Linux only)
+### AMD GPUs (Linux)
+
 AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
 
 ```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4```
 
-This is the command to install the nightly with ROCm 6.4 which might have some performance improvements:
+This is the command to install the nightly with ROCm 7.0 which might have some performance improvements:
 
-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm6.4```
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.0```
+
+
+### AMD GPUs (Experimental: Windows and Linux), RDNA 3, 3.5 and 4 only.
+
+These have less hardware support than the builds above but they work on windows. You also need to install the pytorch version specific to your hardware.
+
+RDNA 3 (RX 7000 series):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/```
+
+RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/```
+
+RDNA 4 (RX 9000 series):
+
+```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/```
 
 ### Intel GPUs (Windows and Linux)
 
@@ -233,7 +257,7 @@ Nvidia users should install stable pytorch using this command:
 
 This is the command to install pytorch nightly instead which might have performance improvements.
 
-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu129```
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130```
 
 #### Troubleshooting
 
@@ -264,12 +288,6 @@ You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS ve
 
 > **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
 
-#### DirectML (AMD Cards on Windows)
-
-This is very badly supported and is not recommended. There are some unofficial builds of pytorch ROCm on windows that exist that will give you a much better experience than this. This readme will be updated once official pytorch ROCm builds for windows come out.
-
-```pip install torch-directml``` Then you can launch ComfyUI with: ```python main.py --directml```
-
 #### Ascend NPUs
 
 For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the [installation](https://ascend.github.io/docs/sources/ascend/quick_install.html) page. Here's a step-by-step guide tailored to your platform and installation method:

app/frontend_management.py

@@ -42,6 +42,7 @@ def get_installed_frontend_version():
     frontend_version_str = version("comfyui-frontend-package")
     return frontend_version_str
 
+
 def get_required_frontend_version():
     """Get the required frontend version from requirements.txt."""
     try:
@@ -63,6 +64,7 @@ def get_required_frontend_version():
         logging.error(f"Error reading requirements.txt: {e}")
         return None
 
+
 def check_frontend_version():
     """Check if the frontend version is up to date."""
 
@@ -203,6 +205,37 @@ class FrontendManager:
         """Get the required frontend package version."""
         return get_required_frontend_version()
 
+    @classmethod
+    def get_installed_templates_version(cls) -> str:
+        """Get the currently installed workflow templates package version."""
+        try:
+            templates_version_str = version("comfyui-workflow-templates")
+            return templates_version_str
+        except Exception:
+            return None
+
+    @classmethod
+    def get_required_templates_version(cls) -> str:
+        """Get the required workflow templates version from requirements.txt."""
+        try:
+            with open(requirements_path, "r", encoding="utf-8") as f:
+                for line in f:
+                    line = line.strip()
+                    if line.startswith("comfyui-workflow-templates=="):
+                        version_str = line.split("==")[-1]
+                        if not is_valid_version(version_str):
+                            logging.error(f"Invalid templates version format in requirements.txt: {version_str}")
+                            return None
+                        return version_str
+                logging.error("comfyui-workflow-templates not found in requirements.txt")
+                return None
+        except FileNotFoundError:
+            logging.error("requirements.txt not found. Cannot determine required templates version.")
+            return None
+        except Exception as e:
+            logging.error(f"Error reading requirements.txt: {e}")
+            return None
+
     @classmethod
     def default_frontend_path(cls) -> str:
         try:

comfy/ldm/ace/vae/music_dcae_pipeline.py

@@ -23,8 +23,6 @@ class MusicDCAE(torch.nn.Module):
         else:
             self.source_sample_rate = source_sample_rate
 
-        # self.resampler = torchaudio.transforms.Resample(source_sample_rate, 44100)
-
         self.transform = transforms.Compose([
             transforms.Normalize(0.5, 0.5),
         ])
@@ -37,10 +35,6 @@ class MusicDCAE(torch.nn.Module):
         self.scale_factor = 0.1786
         self.shift_factor = -1.9091
 
-    def load_audio(self, audio_path):
-        audio, sr = torchaudio.load(audio_path)
-        return audio, sr
-
     def forward_mel(self, audios):
         mels = []
         for i in range(len(audios)):
@@ -73,10 +67,8 @@ class MusicDCAE(torch.nn.Module):
             latent = self.dcae.encoder(mel.unsqueeze(0))
             latents.append(latent)
         latents = torch.cat(latents, dim=0)
-        # latent_lengths = (audio_lengths / sr * 44100 / 512 / self.time_dimention_multiple).long()
         latents = (latents - self.shift_factor) * self.scale_factor
         return latents
-        # return latents, latent_lengths
 
     @torch.no_grad()
     def decode(self, latents, audio_lengths=None, sr=None):
@@ -91,9 +83,7 @@ class MusicDCAE(torch.nn.Module):
             wav = self.vocoder.decode(mels[0]).squeeze(1)
 
             if sr is not None:
-                # resampler = torchaudio.transforms.Resample(44100, sr).to(latents.device).to(latents.dtype)
                 wav = torchaudio.functional.resample(wav, 44100, sr)
-                # wav = resampler(wav)
             else:
                 sr = 44100
             pred_wavs.append(wav)
@@ -101,7 +91,6 @@ class MusicDCAE(torch.nn.Module):
         if audio_lengths is not None:
             pred_wavs = [wav[:, :length].cpu() for wav, length in zip(pred_wavs, audio_lengths)]
         return torch.stack(pred_wavs)
-        # return sr, pred_wavs
 
     def forward(self, audios, audio_lengths=None, sr=None):
         latents, latent_lengths = self.encode(audios=audios, audio_lengths=audio_lengths, sr=sr)

comfy/ldm/flux/math.py

@@ -37,7 +37,10 @@ def rope(pos: Tensor, dim: int, theta: int) -> Tensor:
 
 def apply_rope1(x: Tensor, freqs_cis: Tensor):
     x_ = x.to(dtype=freqs_cis.dtype).reshape(*x.shape[:-1], -1, 1, 2)
-    x_out = freqs_cis[..., 0] * x_[..., 0] + freqs_cis[..., 1] * x_[..., 1]
+
+    x_out = freqs_cis[..., 0] * x_[..., 0]
+    x_out.addcmul_(freqs_cis[..., 1], x_[..., 1])
+
     return x_out.reshape(*x.shape).type_as(x)
 
 def apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor):

comfy/ldm/hunyuan_video/vae_refiner.py

@@ -1,7 +1,7 @@
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from comfy.ldm.modules.diffusionmodules.model import ResnetBlock, AttnBlock, VideoConv3d
+from comfy.ldm.modules.diffusionmodules.model import ResnetBlock, AttnBlock, VideoConv3d, Normalize
 import comfy.ops
 import comfy.ldm.models.autoencoder
 ops = comfy.ops.disable_weight_init
@@ -17,11 +17,12 @@ class RMS_norm(nn.Module):
         return F.normalize(x, dim=1) * self.scale * self.gamma
 
 class DnSmpl(nn.Module):
-    def __init__(self, ic, oc, tds=True):
+    def __init__(self, ic, oc, tds=True, refiner_vae=True, op=VideoConv3d):
         super().__init__()
         fct = 2 * 2 * 2 if tds else 1 * 2 * 2
         assert oc % fct == 0
-        self.conv = VideoConv3d(ic, oc // fct, kernel_size=3)
+        self.conv = op(ic, oc // fct, kernel_size=3, stride=1, padding=1)
+        self.refiner_vae = refiner_vae
 
         self.tds = tds
         self.gs = fct * ic // oc
@@ -30,7 +31,7 @@ class DnSmpl(nn.Module):
         r1 = 2 if self.tds else 1
         h = self.conv(x)
 
-        if self.tds:
+        if self.tds and self.refiner_vae:
             hf = h[:, :, :1, :, :]
             b, c, f, ht, wd = hf.shape
             hf = hf.reshape(b, c, f, ht // 2, 2, wd // 2, 2)
@@ -66,6 +67,7 @@ class DnSmpl(nn.Module):
             sc = torch.cat([xf, xn], dim=2)
         else:
             b, c, frms, ht, wd = h.shape
+
             nf = frms // r1
             h = h.reshape(b, c, nf, r1, ht // 2, 2, wd // 2, 2)
             h = h.permute(0, 3, 5, 7, 1, 2, 4, 6)
@@ -83,10 +85,11 @@ class DnSmpl(nn.Module):
 
 
 class UpSmpl(nn.Module):
-    def __init__(self, ic, oc, tus=True):
+    def __init__(self, ic, oc, tus=True, refiner_vae=True, op=VideoConv3d):
         super().__init__()
         fct = 2 * 2 * 2 if tus else 1 * 2 * 2
-        self.conv = VideoConv3d(ic, oc * fct, kernel_size=3)
+        self.conv = op(ic, oc * fct, kernel_size=3, stride=1, padding=1)
+        self.refiner_vae = refiner_vae
 
         self.tus = tus
         self.rp = fct * oc // ic
@@ -95,7 +98,7 @@ class UpSmpl(nn.Module):
         r1 = 2 if self.tus else 1
         h = self.conv(x)
 
-        if self.tus:
+        if self.tus and self.refiner_vae:
             hf = h[:, :, :1, :, :]
             b, c, f, ht, wd = hf.shape
             nc = c // (2 * 2)
@@ -148,43 +151,56 @@ class UpSmpl(nn.Module):
 
 class Encoder(nn.Module):
     def __init__(self, in_channels, z_channels, block_out_channels, num_res_blocks,
-                 ffactor_spatial, ffactor_temporal, downsample_match_channel=True, **_):
+                 ffactor_spatial, ffactor_temporal, downsample_match_channel=True, refiner_vae=True, **_):
         super().__init__()
         self.z_channels = z_channels
         self.block_out_channels = block_out_channels
         self.num_res_blocks = num_res_blocks
-        self.conv_in = VideoConv3d(in_channels, block_out_channels[0], 3, 1, 1)
+        self.ffactor_temporal = ffactor_temporal
+
+        self.refiner_vae = refiner_vae
+        if self.refiner_vae:
+            conv_op = VideoConv3d
+            norm_op = RMS_norm
+        else:
+            conv_op = ops.Conv3d
+            norm_op = Normalize
+
+        self.conv_in = conv_op(in_channels, block_out_channels[0], 3, 1, 1)
 
         self.down = nn.ModuleList()
         ch = block_out_channels[0]
         depth = (ffactor_spatial >> 1).bit_length()
-        depth_temporal = ((ffactor_spatial // ffactor_temporal) >> 1).bit_length()
+        depth_temporal = ((ffactor_spatial // self.ffactor_temporal) >> 1).bit_length()
 
         for i, tgt in enumerate(block_out_channels):
             stage = nn.Module()
             stage.block = nn.ModuleList([ResnetBlock(in_channels=ch if j == 0 else tgt,
                                                      out_channels=tgt,
                                                      temb_channels=0,
-                                                     conv_op=VideoConv3d, norm_op=RMS_norm)
+                                                     conv_op=conv_op, norm_op=norm_op)
                                         for j in range(num_res_blocks)])
             ch = tgt
             if i < depth:
                 nxt = block_out_channels[i + 1] if i + 1 < len(block_out_channels) and downsample_match_channel else ch
-                stage.downsample = DnSmpl(ch, nxt, tds=i >= depth_temporal)
+                stage.downsample = DnSmpl(ch, nxt, tds=i >= depth_temporal, refiner_vae=self.refiner_vae, op=conv_op)
                 ch = nxt
             self.down.append(stage)
 
         self.mid = nn.Module()
-        self.mid.block_1 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=VideoConv3d, norm_op=RMS_norm)
-        self.mid.attn_1 = AttnBlock(ch, conv_op=ops.Conv3d, norm_op=RMS_norm)
-        self.mid.block_2 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=VideoConv3d, norm_op=RMS_norm)
+        self.mid.block_1 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=conv_op, norm_op=norm_op)
+        self.mid.attn_1 = AttnBlock(ch, conv_op=ops.Conv3d, norm_op=norm_op)
+        self.mid.block_2 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=conv_op, norm_op=norm_op)
 
-        self.norm_out = RMS_norm(ch)
-        self.conv_out = VideoConv3d(ch, z_channels << 1, 3, 1, 1)
+        self.norm_out = norm_op(ch)
+        self.conv_out = conv_op(ch, z_channels << 1, 3, 1, 1)
 
         self.regul = comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer()
 
     def forward(self, x):
+        if not self.refiner_vae and x.shape[2] == 1:
+            x = x.expand(-1, -1, self.ffactor_temporal, -1, -1)
+
         x = self.conv_in(x)
 
         for stage in self.down:
@@ -200,31 +216,42 @@ class Encoder(nn.Module):
         skip = x.view(b, c // grp, grp, t, h, w).mean(2)
 
         out = self.conv_out(F.silu(self.norm_out(x))) + skip
-        out = self.regul(out)[0]
 
-        out = torch.cat((out[:, :, :1], out), dim=2)
-        out = out.permute(0, 2, 1, 3, 4)
-        b, f_times_2, c, h, w = out.shape
-        out = out.reshape(b, f_times_2 // 2, 2 * c, h, w)
-        out = out.permute(0, 2, 1, 3, 4).contiguous()
+        if self.refiner_vae:
+            out = self.regul(out)[0]
+
+            out = torch.cat((out[:, :, :1], out), dim=2)
+            out = out.permute(0, 2, 1, 3, 4)
+            b, f_times_2, c, h, w = out.shape
+            out = out.reshape(b, f_times_2 // 2, 2 * c, h, w)
+            out = out.permute(0, 2, 1, 3, 4).contiguous()
+
         return out
 
 class Decoder(nn.Module):
     def __init__(self, z_channels, out_channels, block_out_channels, num_res_blocks,
-                 ffactor_spatial, ffactor_temporal, upsample_match_channel=True, **_):
+                 ffactor_spatial, ffactor_temporal, upsample_match_channel=True, refiner_vae=True, **_):
         super().__init__()
         block_out_channels = block_out_channels[::-1]
         self.z_channels = z_channels
         self.block_out_channels = block_out_channels
         self.num_res_blocks = num_res_blocks
 
+        self.refiner_vae = refiner_vae
+        if self.refiner_vae:
+            conv_op = VideoConv3d
+            norm_op = RMS_norm
+        else:
+            conv_op = ops.Conv3d
+            norm_op = Normalize
+
         ch = block_out_channels[0]
-        self.conv_in = VideoConv3d(z_channels, ch, 3)
+        self.conv_in = conv_op(z_channels, ch, kernel_size=3, stride=1, padding=1)
 
         self.mid = nn.Module()
-        self.mid.block_1 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=VideoConv3d, norm_op=RMS_norm)
-        self.mid.attn_1 = AttnBlock(ch, conv_op=ops.Conv3d, norm_op=RMS_norm)
-        self.mid.block_2 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=VideoConv3d, norm_op=RMS_norm)
+        self.mid.block_1 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=conv_op, norm_op=norm_op)
+        self.mid.attn_1 = AttnBlock(ch, conv_op=ops.Conv3d, norm_op=norm_op)
+        self.mid.block_2 = ResnetBlock(in_channels=ch, out_channels=ch, temb_channels=0, conv_op=conv_op, norm_op=norm_op)
 
         self.up = nn.ModuleList()
         depth = (ffactor_spatial >> 1).bit_length()
@@ -235,25 +262,26 @@ class Decoder(nn.Module):
             stage.block = nn.ModuleList([ResnetBlock(in_channels=ch if j == 0 else tgt,
                                                      out_channels=tgt,
                                                      temb_channels=0,
-                                                     conv_op=VideoConv3d, norm_op=RMS_norm)
+                                                     conv_op=conv_op, norm_op=norm_op)
                                         for j in range(num_res_blocks + 1)])
             ch = tgt
             if i < depth:
                 nxt = block_out_channels[i + 1] if i + 1 < len(block_out_channels) and upsample_match_channel else ch
-                stage.upsample = UpSmpl(ch, nxt, tus=i < depth_temporal)
+                stage.upsample = UpSmpl(ch, nxt, tus=i < depth_temporal, refiner_vae=self.refiner_vae, op=conv_op)
                 ch = nxt
             self.up.append(stage)
 
-        self.norm_out = RMS_norm(ch)
-        self.conv_out = VideoConv3d(ch, out_channels, 3)
+        self.norm_out = norm_op(ch)
+        self.conv_out = conv_op(ch, out_channels, 3, stride=1, padding=1)
 
     def forward(self, z):
-        z = z.permute(0, 2, 1, 3, 4)
-        b, f, c, h, w = z.shape
-        z = z.reshape(b, f, 2, c // 2, h, w)
-        z = z.permute(0, 1, 2, 3, 4, 5).reshape(b, f * 2, c // 2, h, w)
-        z = z.permute(0, 2, 1, 3, 4)
-        z = z[:, :, 1:]
+        if self.refiner_vae:
+            z = z.permute(0, 2, 1, 3, 4)
+            b, f, c, h, w = z.shape
+            z = z.reshape(b, f, 2, c // 2, h, w)
+            z = z.permute(0, 1, 2, 3, 4, 5).reshape(b, f * 2, c // 2, h, w)
+            z = z.permute(0, 2, 1, 3, 4)
+            z = z[:, :, 1:]
 
         x = self.conv_in(z) + z.repeat_interleave(self.block_out_channels[0] // self.z_channels, 1)
         x = self.mid.block_2(self.mid.attn_1(self.mid.block_1(x)))
@@ -264,4 +292,10 @@ class Decoder(nn.Module):
             if hasattr(stage, 'upsample'):
                 x = stage.upsample(x)
 
-        return self.conv_out(F.silu(self.norm_out(x)))
+        out = self.conv_out(F.silu(self.norm_out(x)))
+
+        if not self.refiner_vae:
+            if z.shape[-3] == 1:
+                out = out[:, :, -1:]
+
+        return out

comfy/ldm/wan/model.py

@@ -237,6 +237,7 @@ class WanAttentionBlock(nn.Module):
             freqs, transformer_options=transformer_options)
 
         x = torch.addcmul(x, y, repeat_e(e[2], x))
+        del y
 
         # cross-attention & ffn
         x = x + self.cross_attn(self.norm3(x), context, context_img_len=context_img_len, transformer_options=transformer_options)
@@ -902,7 +903,7 @@ class MotionEncoder_tc(nn.Module):
     def __init__(self,
                  in_dim: int,
                  hidden_dim: int,
-                 num_heads=int,
+                 num_heads: int,
                  need_global=True,
                  dtype=None,
                  device=None,
@@ -1355,7 +1356,7 @@ class WanT2VCrossAttentionGather(WanSelfAttention):
 
         x = optimized_attention(q, k, v, heads=self.num_heads, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
 
-        x = x.transpose(1, 2).view(b, -1, n, d).flatten(2)
+        x = x.transpose(1, 2).reshape(b, -1, n * d)
         x = self.o(x)
         return x
 

comfy/ldm/wan/vae.py

@@ -468,55 +468,46 @@ class WanVAE(nn.Module):
                                  attn_scales, self.temperal_upsample, dropout)
 
     def encode(self, x):
-        self.clear_cache()
+        conv_idx = [0]
+        feat_map = [None] * count_conv3d(self.decoder)
         ## cache
         t = x.shape[2]
         iter_ = 1 + (t - 1) // 4
         ## 对encode输入的x，按时间拆分为1、4、4、4....
         for i in range(iter_):
-            self._enc_conv_idx = [0]
+            conv_idx = [0]
             if i == 0:
                 out = self.encoder(
                     x[:, :, :1, :, :],
-                    feat_cache=self._enc_feat_map,
-                    feat_idx=self._enc_conv_idx)
+                    feat_cache=feat_map,
+                    feat_idx=conv_idx)
             else:
                 out_ = self.encoder(
                     x[:, :, 1 + 4 * (i - 1):1 + 4 * i, :, :],
-                    feat_cache=self._enc_feat_map,
-                    feat_idx=self._enc_conv_idx)
+                    feat_cache=feat_map,
+                    feat_idx=conv_idx)
                 out = torch.cat([out, out_], 2)
         mu, log_var = self.conv1(out).chunk(2, dim=1)
-        self.clear_cache()
         return mu
 
     def decode(self, z):
-        self.clear_cache()
+        conv_idx = [0]
+        feat_map = [None] * count_conv3d(self.decoder)
         # z: [b,c,t,h,w]
 
         iter_ = z.shape[2]
         x = self.conv2(z)
         for i in range(iter_):
-            self._conv_idx = [0]
+            conv_idx = [0]
             if i == 0:
                 out = self.decoder(
                     x[:, :, i:i + 1, :, :],
-                    feat_cache=self._feat_map,
-                    feat_idx=self._conv_idx)
+                    feat_cache=feat_map,
+                    feat_idx=conv_idx)
             else:
                 out_ = self.decoder(
                     x[:, :, i:i + 1, :, :],
-                    feat_cache=self._feat_map,
-                    feat_idx=self._conv_idx)
+                    feat_cache=feat_map,
+                    feat_idx=conv_idx)
                 out = torch.cat([out, out_], 2)
-        self.clear_cache()
         return out
-
-    def clear_cache(self):
-        self._conv_num = count_conv3d(self.decoder)
-        self._conv_idx = [0]
-        self._feat_map = [None] * self._conv_num
-        #cache encode
-        self._enc_conv_num = count_conv3d(self.encoder)
-        self._enc_conv_idx = [0]
-        self._enc_feat_map = [None] * self._enc_conv_num

comfy/model_management.py

@@ -645,7 +645,9 @@ def load_models_gpu(models, memory_required=0, force_patch_weights=False, minimu
             if loaded_model.model.is_clone(current_loaded_models[i].model):
                 to_unload = [i] + to_unload
         for i in to_unload:
-            current_loaded_models.pop(i).model.detach(unpatch_all=False)
+            model_to_unload = current_loaded_models.pop(i)
+            model_to_unload.model.detach(unpatch_all=False)
+            model_to_unload.model_finalizer.detach()
 
     total_memory_required = {}
     for loaded_model in models_to_load:

comfy/samplers.py

@@ -360,7 +360,7 @@ def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
 def cfg_function(model, cond_pred, uncond_pred, cond_scale, x, timestep, model_options={}, cond=None, uncond=None):
     if "sampler_cfg_function" in model_options:
         args = {"cond": x - cond_pred, "uncond": x - uncond_pred, "cond_scale": cond_scale, "timestep": timestep, "input": x, "sigma": timestep,
-                "cond_denoised": cond_pred, "uncond_denoised": uncond_pred, "model": model, "model_options": model_options}
+                "cond_denoised": cond_pred, "uncond_denoised": uncond_pred, "model": model, "model_options": model_options, "input_cond": cond, "input_uncond": uncond}
         cfg_result = x - model_options["sampler_cfg_function"](args)
     else:
         cfg_result = uncond_pred + (cond_pred - uncond_pred) * cond_scale
@@ -390,7 +390,7 @@ def sampling_function(model, x, timestep, uncond, cond, cond_scale, model_option
     for fn in model_options.get("sampler_pre_cfg_function", []):
         args = {"conds":conds, "conds_out": out, "cond_scale": cond_scale, "timestep": timestep,
                 "input": x, "sigma": timestep, "model": model, "model_options": model_options}
-        out  = fn(args)
+        out = fn(args)
 
     return cfg_function(model, out[0], out[1], cond_scale, x, timestep, model_options=model_options, cond=cond, uncond=uncond_)
 

comfy/sd.py

@@ -332,35 +332,51 @@ class VAE:
                 self.first_stage_model = StageC_coder()
                 self.downscale_ratio = 32
                 self.latent_channels = 16
-            elif "decoder.conv_in.weight" in sd and sd['decoder.conv_in.weight'].shape[1] == 64:
-                ddconfig = {"block_out_channels": [128, 256, 512, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 32, "downsample_match_channel": True, "upsample_match_channel": True}
-                self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
-                self.downscale_ratio = 32
-                self.upscale_ratio = 32
-                self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
-                self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
-                                                            encoder_config={'target': "comfy.ldm.hunyuan_video.vae.Encoder", 'params': ddconfig},
-                                                            decoder_config={'target': "comfy.ldm.hunyuan_video.vae.Decoder", 'params': ddconfig})
-
-                self.memory_used_encode = lambda shape, dtype: (700 * shape[2] * shape[3]) * model_management.dtype_size(dtype)
-                self.memory_used_decode = lambda shape, dtype: (700 * shape[2] * shape[3] * 32 * 32) * model_management.dtype_size(dtype)
-
             elif "decoder.conv_in.weight" in sd:
-                #default SD1.x/SD2.x VAE parameters
-                ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}
-
-                if 'encoder.down.2.downsample.conv.weight' not in sd and 'decoder.up.3.upsample.conv.weight' not in sd: #Stable diffusion x4 upscaler VAE
-                    ddconfig['ch_mult'] = [1, 2, 4]
-                    self.downscale_ratio = 4
-                    self.upscale_ratio = 4
-
-                self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
-                if 'post_quant_conv.weight' in sd:
-                    self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])
-                else:
+                if sd['decoder.conv_in.weight'].shape[1] == 64:
+                    ddconfig = {"block_out_channels": [128, 256, 512, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 32, "downsample_match_channel": True, "upsample_match_channel": True}
+                    self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
+                    self.downscale_ratio = 32
+                    self.upscale_ratio = 32
+                    self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
                     self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
-                                                                encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig},
-                                                                decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
+                                                                encoder_config={'target': "comfy.ldm.hunyuan_video.vae.Encoder", 'params': ddconfig},
+                                                                decoder_config={'target': "comfy.ldm.hunyuan_video.vae.Decoder", 'params': ddconfig})
+
+                    self.memory_used_encode = lambda shape, dtype: (700 * shape[2] * shape[3]) * model_management.dtype_size(dtype)
+                    self.memory_used_decode = lambda shape, dtype: (700 * shape[2] * shape[3] * 32 * 32) * model_management.dtype_size(dtype)
+                elif sd['decoder.conv_in.weight'].shape[1] == 32:
+                    ddconfig = {"block_out_channels": [128, 256, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 16, "ffactor_temporal": 4, "downsample_match_channel": True, "upsample_match_channel": True, "refiner_vae": False}
+                    self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
+                    self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
+                    self.upscale_ratio = (lambda a: max(0, a * 4 - 3), 16, 16)
+                    self.upscale_index_formula = (4, 16, 16)
+                    self.downscale_ratio = (lambda a: max(0, math.floor((a + 3) / 4)), 16, 16)
+                    self.downscale_index_formula = (4, 16, 16)
+                    self.latent_dim = 3
+                    self.not_video = True
+                    self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
+                                                                encoder_config={'target': "comfy.ldm.hunyuan_video.vae_refiner.Encoder", 'params': ddconfig},
+                                                                decoder_config={'target': "comfy.ldm.hunyuan_video.vae_refiner.Decoder", 'params': ddconfig})
+
+                    self.memory_used_encode = lambda shape, dtype: (2800 * shape[-2] * shape[-1]) * model_management.dtype_size(dtype)
+                    self.memory_used_decode = lambda shape, dtype: (2800 * shape[-3] * shape[-2] * shape[-1] * 16 * 16) * model_management.dtype_size(dtype)
+                else:
+                    #default SD1.x/SD2.x VAE parameters
+                    ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}
+
+                    if 'encoder.down.2.downsample.conv.weight' not in sd and 'decoder.up.3.upsample.conv.weight' not in sd: #Stable diffusion x4 upscaler VAE
+                        ddconfig['ch_mult'] = [1, 2, 4]
+                        self.downscale_ratio = 4
+                        self.upscale_ratio = 4
+
+                    self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.weight"].shape[1]
+                    if 'post_quant_conv.weight' in sd:
+                        self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])
+                    else:
+                        self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
+                                                                    encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig},
+                                                                    decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
             elif "decoder.layers.1.layers.0.beta" in sd:
                 self.first_stage_model = AudioOobleckVAE()
                 self.memory_used_encode = lambda shape, dtype: (1000 * shape[2]) * model_management.dtype_size(dtype)
@@ -636,6 +652,7 @@ class VAE:
     def decode(self, samples_in, vae_options={}):
         self.throw_exception_if_invalid()
         pixel_samples = None
+        do_tile = False
         try:
             memory_used = self.memory_used_decode(samples_in.shape, self.vae_dtype)
             model_management.load_models_gpu([self.patcher], memory_required=memory_used, force_full_load=self.disable_offload)
@@ -651,6 +668,13 @@ class VAE:
                 pixel_samples[x:x+batch_number] = out
         except model_management.OOM_EXCEPTION:
             logging.warning("Warning: Ran out of memory when regular VAE decoding, retrying with tiled VAE decoding.")
+            #NOTE: We don't know what tensors were allocated to stack variables at the time of the
+            #exception and the exception itself refs them all until we get out of this except block.
+            #So we just set a flag for tiler fallback so that tensor gc can happen once the
+            #exception is fully off the books.
+            do_tile = True
+
+        if do_tile:
             dims = samples_in.ndim - 2
             if dims == 1 or self.extra_1d_channel is not None:
                 pixel_samples = self.decode_tiled_1d(samples_in)
@@ -697,6 +721,7 @@ class VAE:
         self.throw_exception_if_invalid()
         pixel_samples = self.vae_encode_crop_pixels(pixel_samples)
         pixel_samples = pixel_samples.movedim(-1, 1)
+        do_tile = False
         if self.latent_dim == 3 and pixel_samples.ndim < 5:
             if not self.not_video:
                 pixel_samples = pixel_samples.movedim(1, 0).unsqueeze(0)
@@ -718,6 +743,13 @@ class VAE:
 
         except model_management.OOM_EXCEPTION:
             logging.warning("Warning: Ran out of memory when regular VAE encoding, retrying with tiled VAE encoding.")
+            #NOTE: We don't know what tensors were allocated to stack variables at the time of the
+            #exception and the exception itself refs them all until we get out of this except block.
+            #So we just set a flag for tiler fallback so that tensor gc can happen once the
+            #exception is fully off the books.
+            do_tile = True
+
+        if do_tile:
             if self.latent_dim == 3:
                 tile = 256
                 overlap = tile // 4

comfy/text_encoders/hunyuan_image.py

@@ -63,7 +63,13 @@ class HunyuanImageTEModel(QwenImageTEModel):
             self.byt5_small = None
 
     def encode_token_weights(self, token_weight_pairs):
-        cond, p, extra = super().encode_token_weights(token_weight_pairs)
+        tok_pairs = token_weight_pairs["qwen25_7b"][0]
+        template_end = -1
+        if tok_pairs[0][0] == 27:
+            if len(tok_pairs) > 36:  # refiner prompt uses a fixed 36 template_end
+                template_end = 36
+
+        cond, p, extra = super().encode_token_weights(token_weight_pairs, template_end=template_end)
         if self.byt5_small is not None and "byt5" in token_weight_pairs:
             out = self.byt5_small.encode_token_weights(token_weight_pairs["byt5"])
             extra["conditioning_byt5small"] = out[0]

comfy/text_encoders/qwen_image.py

@@ -18,13 +18,22 @@ class QwenImageTokenizer(sd1_clip.SD1Tokenizer):
         self.llama_template_images = "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n"
 
     def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], **kwargs):
-        if llama_template is None:
-            if len(images) > 0:
-                llama_text = self.llama_template_images.format(text)
-            else:
-                llama_text = self.llama_template.format(text)
+        skip_template = False
+        if text.startswith('<|im_start|>'):
+            skip_template = True
+        if text.startswith('<|start_header_id|>'):
+            skip_template = True
+
+        if skip_template:
+            llama_text = text
         else:
-            llama_text = llama_template.format(text)
+            if llama_template is None:
+                if len(images) > 0:
+                    llama_text = self.llama_template_images.format(text)
+                else:
+                    llama_text = self.llama_template.format(text)
+            else:
+                llama_text = llama_template.format(text)
         tokens = super().tokenize_with_weights(llama_text, return_word_ids=return_word_ids, disable_weights=True, **kwargs)
         key_name = next(iter(tokens))
         embed_count = 0
@@ -47,22 +56,23 @@ class QwenImageTEModel(sd1_clip.SD1ClipModel):
     def __init__(self, device="cpu", dtype=None, model_options={}):
         super().__init__(device=device, dtype=dtype, name="qwen25_7b", clip_model=Qwen25_7BVLIModel, model_options=model_options)
 
-    def encode_token_weights(self, token_weight_pairs):
+    def encode_token_weights(self, token_weight_pairs, template_end=-1):
         out, pooled, extra = super().encode_token_weights(token_weight_pairs)
         tok_pairs = token_weight_pairs["qwen25_7b"][0]
         count_im_start = 0
-        for i, v in enumerate(tok_pairs):
-            elem = v[0]
-            if not torch.is_tensor(elem):
-                if isinstance(elem, numbers.Integral):
-                    if elem == 151644 and count_im_start < 2:
-                        template_end = i
-                        count_im_start += 1
+        if template_end == -1:
+            for i, v in enumerate(tok_pairs):
+                elem = v[0]
+                if not torch.is_tensor(elem):
+                    if isinstance(elem, numbers.Integral):
+                        if elem == 151644 and count_im_start < 2:
+                            template_end = i
+                            count_im_start += 1
 
-        if out.shape[1] > (template_end + 3):
-            if tok_pairs[template_end + 1][0] == 872:
-                if tok_pairs[template_end + 2][0] == 198:
-                    template_end += 3
+            if out.shape[1] > (template_end + 3):
+                if tok_pairs[template_end + 1][0] == 872:
+                    if tok_pairs[template_end + 2][0] == 198:
+                        template_end += 3
 
         out = out[:, template_end:]
 

comfy_api/latest/_io.py

@@ -1605,6 +1605,7 @@ class _IO:
     Model = Model
     ClipVision = ClipVision
     ClipVisionOutput = ClipVisionOutput
+    AudioEncoder = AudioEncoder
     AudioEncoderOutput = AudioEncoderOutput
     StyleModel = StyleModel
     Gligen = Gligen

comfy_api_nodes/apis/__init__.py

@@ -2,6 +2,7 @@
 #   filename:  filtered-openapi.yaml
 #   timestamp: 2025-07-30T08:54:00+00:00
 
+# pylint: disable
 from __future__ import annotations
 
 from datetime import date, datetime
@@ -1320,6 +1321,7 @@ class KlingTextToVideoModelName(str, Enum):
     kling_v1 = 'kling-v1'
     kling_v1_6 = 'kling-v1-6'
     kling_v2_1_master = 'kling-v2-1-master'
+    kling_v2_5_turbo = 'kling-v2-5-turbo'
 
 
 class KlingVideoGenAspectRatio(str, Enum):
@@ -1354,6 +1356,7 @@ class KlingVideoGenModelName(str, Enum):
     kling_v2_master = 'kling-v2-master'
     kling_v2_1 = 'kling-v2-1'
     kling_v2_1_master = 'kling-v2-1-master'
+    kling_v2_5_turbo = 'kling-v2-5-turbo'
 
 
 class KlingVideoResult(BaseModel):

comfy_api_nodes/apis/client.py

@@ -95,6 +95,7 @@ import aiohttp
 import asyncio
 import logging
 import io
+import os
 import socket
 from aiohttp.client_exceptions import ClientError, ClientResponseError
 from typing import Dict, Type, Optional, Any, TypeVar, Generic, Callable, Tuple
@@ -499,7 +500,9 @@ class ApiClient:
         else:
             raise ValueError("File must be BytesIO or str path")
 
-        operation_id = f"upload_{upload_url.split('/')[-1]}_{uuid.uuid4().hex[:8]}"
+        parsed = urlparse(upload_url)
+        basename = os.path.basename(parsed.path) or parsed.netloc or "upload"
+        operation_id = f"upload_{basename}_{uuid.uuid4().hex[:8]}"
         request_logger.log_request_response(
             operation_id=operation_id,
             request_method="PUT",
@@ -532,7 +535,7 @@ class ApiClient:
                     request_method="PUT",
                     request_url=upload_url,
                     response_status_code=e.status if hasattr(e, "status") else None,
-                    response_headers=dict(e.headers) if getattr(e, "headers") else None,
+                    response_headers=dict(e.headers) if hasattr(e, "headers") else None,
                     response_content=None,
                     error_message=f"{type(e).__name__}: {str(e)}",
                 )

comfy_api_nodes/apis/request_logger.py

@@ -4,16 +4,18 @@ import os
 import datetime
 import json
 import logging
+import re
+import hashlib
+from typing import Any
+
 import folder_paths
 
 # Get the logger instance
 logger = logging.getLogger(__name__)
 
+
 def get_log_directory():
-    """
-    Ensures the API log directory exists within ComfyUI's temp directory
-    and returns its path.
-    """
+    """Ensures the API log directory exists within ComfyUI's temp directory and returns its path."""
     base_temp_dir = folder_paths.get_temp_directory()
     log_dir = os.path.join(base_temp_dir, "api_logs")
     try:
@@ -24,42 +26,77 @@ def get_log_directory():
         return base_temp_dir
     return log_dir
 
-def _format_data_for_logging(data):
+
+def _sanitize_filename_component(name: str) -> str:
+    if not name:
+        return "log"
+    sanitized = re.sub(r"[^A-Za-z0-9._-]+", "_", name)  # Replace disallowed characters with underscore
+    sanitized = sanitized.strip(" ._")  # Windows: trailing dots or spaces are not allowed
+    if not sanitized:
+        sanitized = "log"
+    return sanitized
+
+
+def _short_hash(*parts: str, length: int = 10) -> str:
+    return hashlib.sha1(("|".join(parts)).encode("utf-8")).hexdigest()[:length]
+
+
+def _build_log_filepath(log_dir: str, operation_id: str, request_url: str) -> str:
+    """Build log filepath. We keep it well under common path length limits aiming for <= 240 characters total."""
+    timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S_%f")
+    slug = _sanitize_filename_component(operation_id)  # Best-effort human-readable slug from operation_id
+    h = _short_hash(operation_id or "", request_url or "")  # Short hash ties log to the full operation and URL
+
+    # Compute how much room we have for the slug given the directory length
+    # Keep total path length reasonably below ~260 on Windows.
+    max_total_path = 240
+    prefix = f"{timestamp}_"
+    suffix = f"_{h}.log"
+    if not slug:
+        slug = "op"
+    max_filename_len = max(60, max_total_path - len(log_dir) - 1)
+    max_slug_len = max(8, max_filename_len - len(prefix) - len(suffix))
+    if len(slug) > max_slug_len:
+        slug = slug[:max_slug_len].rstrip(" ._-")
+    return os.path.join(log_dir, f"{prefix}{slug}{suffix}")
+
+
+def _format_data_for_logging(data: Any) -> str:
     """Helper to format data (dict, str, bytes) for logging."""
     if isinstance(data, bytes):
         try:
-            return data.decode('utf-8')  # Try to decode as text
+            return data.decode("utf-8")  # Try to decode as text
         except UnicodeDecodeError:
             return f"[Binary data of length {len(data)} bytes]"
     elif isinstance(data, (dict, list)):
         try:
             return json.dumps(data, indent=2, ensure_ascii=False)
         except TypeError:
-            return str(data) # Fallback for non-serializable objects
+            return str(data)  # Fallback for non-serializable objects
     return str(data)
 
+
 def log_request_response(
     operation_id: str,
     request_method: str,
     request_url: str,
     request_headers: dict | None = None,
     request_params: dict | None = None,
-    request_data: any = None,
+    request_data: Any = None,
     response_status_code: int | None = None,
     response_headers: dict | None = None,
-    response_content: any = None,
-    error_message: str | None = None
+    response_content: Any = None,
+    error_message: str | None = None,
 ):
     """
     Logs API request and response details to a file in the temp/api_logs directory.
+    Filenames are sanitized and length-limited for cross-platform safety.
+    If we still fail to write, we fall back to appending into api.log.
     """
     log_dir = get_log_directory()
-    timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S_%f")
-    filename = f"{timestamp}_{operation_id.replace('/', '_').replace(':', '_')}.log"
-    filepath = os.path.join(log_dir, filename)
-
-    log_content = []
+    filepath = _build_log_filepath(log_dir, operation_id, request_url)
 
+    log_content: list[str] = []
     log_content.append(f"Timestamp: {datetime.datetime.now().isoformat()}")
     log_content.append(f"Operation ID: {operation_id}")
     log_content.append("-" * 30 + " REQUEST " + "-" * 30)
@@ -69,7 +106,7 @@ def log_request_response(
         log_content.append(f"Headers:\n{_format_data_for_logging(request_headers)}")
     if request_params:
         log_content.append(f"Params:\n{_format_data_for_logging(request_params)}")
-    if request_data:
+    if request_data is not None:
         log_content.append(f"Data/Body:\n{_format_data_for_logging(request_data)}")
 
     log_content.append("\n" + "-" * 30 + " RESPONSE " + "-" * 30)
@@ -77,7 +114,7 @@ def log_request_response(
         log_content.append(f"Status Code: {response_status_code}")
     if response_headers:
         log_content.append(f"Headers:\n{_format_data_for_logging(response_headers)}")
-    if response_content:
+    if response_content is not None:
         log_content.append(f"Content:\n{_format_data_for_logging(response_content)}")
     if error_message:
         log_content.append(f"Error:\n{error_message}")
@@ -89,6 +126,7 @@ def log_request_response(
     except Exception as e:
         logger.error(f"Error writing API log to {filepath}: {e}")
 
+
 if __name__ == '__main__':
     # Example usage (for testing the logger directly)
     logger.setLevel(logging.DEBUG)

comfy_api_nodes/apis/rodin_api.py

@@ -9,8 +9,9 @@ class Rodin3DGenerateRequest(BaseModel):
     seed: int = Field(..., description="seed_")
     tier: str = Field(..., description="Tier of generation.")
     material: str = Field(..., description="The material type.")
-    quality: str = Field(..., description="The generation quality of the mesh.")
+    quality_override: int = Field(..., description="The poly count of the mesh.")
     mesh_mode: str = Field(..., description="It controls the type of faces of generated models.")
+    TAPose: Optional[bool] = Field(None, description="")
 
 class GenerateJobsData(BaseModel):
     uuids: List[str] = Field(..., description="str LIST")
@@ -51,7 +52,3 @@ class RodinResourceItem(BaseModel):
 
 class Rodin3DDownloadResponse(BaseModel):
     list: List[RodinResourceItem] = Field(..., description="Source List")
-
-
-
-

comfy_api_nodes/nodes_bytedance.py

@@ -920,7 +920,7 @@ class ByteDanceFirstLastFrameNode(comfy_io.ComfyNode):
             inputs=[
                 comfy_io.Combo.Input(
                     "model",
-                    options=[Image2VideoModelName.seedance_1_lite.value],
+                    options=[model.value for model in Image2VideoModelName],
                     default=Image2VideoModelName.seedance_1_lite.value,
                     tooltip="Model name",
                 ),

comfy_api_nodes/nodes_gemini.py

@@ -39,6 +39,7 @@ from comfy_api_nodes.apinode_utils import (
     tensor_to_base64_string,
     bytesio_to_image_tensor,
 )
+from comfy_api.util import VideoContainer, VideoCodec
 
 
 GEMINI_BASE_ENDPOINT = "/proxy/vertexai/gemini"
@@ -310,7 +311,7 @@ class GeminiNode(ComfyNodeABC):
         Returns:
             List of GeminiPart objects containing the encoded video.
         """
-        from comfy_api.util import VideoContainer, VideoCodec
+
         base_64_string = video_to_base64_string(
             video_input,
             container_format=VideoContainer.MP4,
@@ -490,7 +491,6 @@ class GeminiInputFiles(ComfyNodeABC):
         # Use base64 string directly, not the data URI
         with open(file_path, "rb") as f:
             file_content = f.read()
-        import base64
         base64_str = base64.b64encode(file_content).decode("utf-8")
 
         return GeminiPart(

comfy_api_nodes/nodes_kling.py

@@ -423,6 +423,8 @@ class KlingTextToVideoNode(KlingNodeBase):
             "standard mode / 10s duration / kling-v2-master": ("std", "10", "kling-v2-master"),
             "pro mode / 5s duration / kling-v2-1-master": ("pro", "5", "kling-v2-1-master"),
             "pro mode / 10s duration / kling-v2-1-master": ("pro", "10", "kling-v2-1-master"),
+            "pro mode / 5s duration / kling-v2-5-turbo": ("pro", "5", "kling-v2-5-turbo"),
+            "pro mode / 10s duration / kling-v2-5-turbo": ("pro", "10", "kling-v2-5-turbo"),
         }
 
     @classmethod
@@ -710,6 +712,9 @@ class KlingImage2VideoNode(KlingNodeBase):
             # Camera control type for image 2 video is always `simple`
             camera_control.type = KlingCameraControlType.simple
 
+        if mode == "std" and model_name == KlingVideoGenModelName.kling_v2_5_turbo.value:
+            mode = "pro"  # October 5: currently "std" mode is not supported for this model
+
         initial_operation = SynchronousOperation(
             endpoint=ApiEndpoint(
                 path=PATH_IMAGE_TO_VIDEO,

comfy_api_nodes/nodes_luma.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 from inspect import cleandoc
 from typing import Optional
-from comfy.comfy_types.node_typing import IO, ComfyNodeABC
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io as comfy_io
 from comfy_api.input_impl.video_types import VideoFromFile
 from comfy_api_nodes.apis.luma_api import (
     LumaImageModel,
@@ -51,174 +52,186 @@ def image_result_url_extractor(response: LumaGeneration):
 def video_result_url_extractor(response: LumaGeneration):
     return response.assets.video if hasattr(response, "assets") and hasattr(response.assets, "video") else None
 
-class LumaReferenceNode(ComfyNodeABC):
+class LumaReferenceNode(comfy_io.ComfyNode):
     """
     Holds an image and weight for use with Luma Generate Image node.
     """
 
-    RETURN_TYPES = (LumaIO.LUMA_REF,)
-    RETURN_NAMES = ("luma_ref",)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "create_luma_reference"
-    CATEGORY = "api node/image/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaReferenceNode",
+            display_name="Luma Reference",
+            category="api node/image/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input(
+                    "image",
+                    tooltip="Image to use as reference.",
+                ),
+                comfy_io.Float.Input(
+                    "weight",
+                    default=1.0,
+                    min=0.0,
+                    max=1.0,
+                    step=0.01,
+                    tooltip="Weight of image reference.",
+                ),
+                comfy_io.Custom(LumaIO.LUMA_REF).Input(
+                    "luma_ref",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Custom(LumaIO.LUMA_REF).Output(display_name="luma_ref")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": (
-                    IO.IMAGE,
-                    {
-                        "tooltip": "Image to use as reference.",
-                    },
-                ),
-                "weight": (
-                    IO.FLOAT,
-                    {
-                        "default": 1.0,
-                        "min": 0.0,
-                        "max": 1.0,
-                        "step": 0.01,
-                        "tooltip": "Weight of image reference.",
-                    },
-                ),
-            },
-            "optional": {"luma_ref": (LumaIO.LUMA_REF,)},
-        }
-
-    def create_luma_reference(
-        self, image: torch.Tensor, weight: float, luma_ref: LumaReferenceChain = None
-    ):
+    def execute(
+        cls, image: torch.Tensor, weight: float, luma_ref: LumaReferenceChain = None
+    ) -> comfy_io.NodeOutput:
         if luma_ref is not None:
             luma_ref = luma_ref.clone()
         else:
             luma_ref = LumaReferenceChain()
         luma_ref.add(LumaReference(image=image, weight=round(weight, 2)))
-        return (luma_ref,)
+        return comfy_io.NodeOutput(luma_ref)
 
 
-class LumaConceptsNode(ComfyNodeABC):
+class LumaConceptsNode(comfy_io.ComfyNode):
     """
     Holds one or more Camera Concepts for use with Luma Text to Video and Luma Image to Video nodes.
     """
 
-    RETURN_TYPES = (LumaIO.LUMA_CONCEPTS,)
-    RETURN_NAMES = ("luma_concepts",)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "create_concepts"
-    CATEGORY = "api node/video/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaConceptsNode",
+            display_name="Luma Concepts",
+            category="api node/video/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Combo.Input(
+                    "concept1",
+                    options=get_luma_concepts(include_none=True),
+                ),
+                comfy_io.Combo.Input(
+                    "concept2",
+                    options=get_luma_concepts(include_none=True),
+                ),
+                comfy_io.Combo.Input(
+                    "concept3",
+                    options=get_luma_concepts(include_none=True),
+                ),
+                comfy_io.Combo.Input(
+                    "concept4",
+                    options=get_luma_concepts(include_none=True),
+                ),
+                comfy_io.Custom(LumaIO.LUMA_CONCEPTS).Input(
+                    "luma_concepts",
+                    tooltip="Optional Camera Concepts to add to the ones chosen here.",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Custom(LumaIO.LUMA_CONCEPTS).Output(display_name="luma_concepts")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "concept1": (get_luma_concepts(include_none=True),),
-                "concept2": (get_luma_concepts(include_none=True),),
-                "concept3": (get_luma_concepts(include_none=True),),
-                "concept4": (get_luma_concepts(include_none=True),),
-            },
-            "optional": {
-                "luma_concepts": (
-                    LumaIO.LUMA_CONCEPTS,
-                    {
-                        "tooltip": "Optional Camera Concepts to add to the ones chosen here."
-                    },
-                ),
-            },
-        }
-
-    def create_concepts(
-        self,
+    def execute(
+        cls,
         concept1: str,
         concept2: str,
         concept3: str,
         concept4: str,
         luma_concepts: LumaConceptChain = None,
-    ):
+    ) -> comfy_io.NodeOutput:
         chain = LumaConceptChain(str_list=[concept1, concept2, concept3, concept4])
         if luma_concepts is not None:
             chain = luma_concepts.clone_and_merge(chain)
-        return (chain,)
+        return comfy_io.NodeOutput(chain)
 
 
-class LumaImageGenerationNode(ComfyNodeABC):
+class LumaImageGenerationNode(comfy_io.ComfyNode):
     """
     Generates images synchronously based on prompt and aspect ratio.
     """
 
-    RETURN_TYPES = (IO.IMAGE,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/image/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaImageNode",
+            display_name="Luma Text to Image",
+            category="api node/image/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the image generation",
+                ),
+                comfy_io.Combo.Input(
+                    "model",
+                    options=[model.value for model in LumaImageModel],
+                ),
+                comfy_io.Combo.Input(
+                    "aspect_ratio",
+                    options=[ratio.value for ratio in LumaAspectRatio],
+                    default=LumaAspectRatio.ratio_16_9,
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
+                ),
+                comfy_io.Float.Input(
+                    "style_image_weight",
+                    default=1.0,
+                    min=0.0,
+                    max=1.0,
+                    step=0.01,
+                    tooltip="Weight of style image. Ignored if no style_image provided.",
+                ),
+                comfy_io.Custom(LumaIO.LUMA_REF).Input(
+                    "image_luma_ref",
+                    tooltip="Luma Reference node connection to influence generation with input images; up to 4 images can be considered.",
+                    optional=True,
+                ),
+                comfy_io.Image.Input(
+                    "style_image",
+                    tooltip="Style reference image; only 1 image will be used.",
+                    optional=True,
+                ),
+                comfy_io.Image.Input(
+                    "character_image",
+                    tooltip="Character reference images; can be a batch of multiple, up to 4 images can be considered.",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Image.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the image generation",
-                    },
-                ),
-                "model": ([model.value for model in LumaImageModel],),
-                "aspect_ratio": (
-                    [ratio.value for ratio in LumaAspectRatio],
-                    {
-                        "default": LumaAspectRatio.ratio_16_9,
-                    },
-                ),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 0xFFFFFFFFFFFFFFFF,
-                        "control_after_generate": True,
-                        "tooltip": "Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
-                    },
-                ),
-                "style_image_weight": (
-                    IO.FLOAT,
-                    {
-                        "default": 1.0,
-                        "min": 0.0,
-                        "max": 1.0,
-                        "step": 0.01,
-                        "tooltip": "Weight of style image. Ignored if no style_image provided.",
-                    },
-                ),
-            },
-            "optional": {
-                "image_luma_ref": (
-                    LumaIO.LUMA_REF,
-                    {
-                        "tooltip": "Luma Reference node connection to influence generation with input images; up to 4 images can be considered."
-                    },
-                ),
-                "style_image": (
-                    IO.IMAGE,
-                    {"tooltip": "Style reference image; only 1 image will be used."},
-                ),
-                "character_image": (
-                    IO.IMAGE,
-                    {
-                        "tooltip": "Character reference images; can be a batch of multiple, up to 4 images can be considered."
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         prompt: str,
         model: str,
         aspect_ratio: str,
@@ -227,27 +240,29 @@ class LumaImageGenerationNode(ComfyNodeABC):
         image_luma_ref: LumaReferenceChain = None,
         style_image: torch.Tensor = None,
         character_image: torch.Tensor = None,
-        unique_id: str = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         validate_string(prompt, strip_whitespace=True, min_length=3)
+        auth_kwargs = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
         # handle image_luma_ref
         api_image_ref = None
         if image_luma_ref is not None:
-            api_image_ref = await self._convert_luma_refs(
-                image_luma_ref, max_refs=4, auth_kwargs=kwargs,
+            api_image_ref = await cls._convert_luma_refs(
+                image_luma_ref, max_refs=4, auth_kwargs=auth_kwargs,
             )
         # handle style_luma_ref
         api_style_ref = None
         if style_image is not None:
-            api_style_ref = await self._convert_style_image(
-                style_image, weight=style_image_weight, auth_kwargs=kwargs,
+            api_style_ref = await cls._convert_style_image(
+                style_image, weight=style_image_weight, auth_kwargs=auth_kwargs,
             )
         # handle character_ref images
         character_ref = None
         if character_image is not None:
             download_urls = await upload_images_to_comfyapi(
-                character_image, max_images=4, auth_kwargs=kwargs,
+                character_image, max_images=4, auth_kwargs=auth_kwargs,
             )
             character_ref = LumaCharacterRef(
                 identity0=LumaImageIdentity(images=download_urls)
@@ -268,7 +283,7 @@ class LumaImageGenerationNode(ComfyNodeABC):
                 style_ref=api_style_ref,
                 character_ref=character_ref,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_api: LumaGeneration = await operation.execute()
 
@@ -283,18 +298,19 @@ class LumaImageGenerationNode(ComfyNodeABC):
             failed_statuses=[LumaState.failed],
             status_extractor=lambda x: x.state,
             result_url_extractor=image_result_url_extractor,
-            node_id=unique_id,
-            auth_kwargs=kwargs,
+            node_id=cls.hidden.unique_id,
+            auth_kwargs=auth_kwargs,
         )
         response_poll = await operation.execute()
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.assets.image) as img_response:
                 img = process_image_response(await img_response.content.read())
-        return (img,)
+        return comfy_io.NodeOutput(img)
 
+    @classmethod
     async def _convert_luma_refs(
-        self, luma_ref: LumaReferenceChain, max_refs: int, auth_kwargs: Optional[dict[str,str]] = None
+        cls, luma_ref: LumaReferenceChain, max_refs: int, auth_kwargs: Optional[dict[str,str]] = None
     ):
         luma_urls = []
         ref_count = 0
@@ -308,82 +324,84 @@ class LumaImageGenerationNode(ComfyNodeABC):
                 break
         return luma_ref.create_api_model(download_urls=luma_urls, max_refs=max_refs)
 
+    @classmethod
     async def _convert_style_image(
-        self, style_image: torch.Tensor, weight: float, auth_kwargs: Optional[dict[str,str]] = None
+        cls, style_image: torch.Tensor, weight: float, auth_kwargs: Optional[dict[str,str]] = None
     ):
         chain = LumaReferenceChain(
             first_ref=LumaReference(image=style_image, weight=weight)
         )
-        return await self._convert_luma_refs(chain, max_refs=1, auth_kwargs=auth_kwargs)
+        return await cls._convert_luma_refs(chain, max_refs=1, auth_kwargs=auth_kwargs)
 
 
-class LumaImageModifyNode(ComfyNodeABC):
+class LumaImageModifyNode(comfy_io.ComfyNode):
     """
     Modifies images synchronously based on prompt and aspect ratio.
     """
 
-    RETURN_TYPES = (IO.IMAGE,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/image/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaImageModifyNode",
+            display_name="Luma Image to Image",
+            category="api node/image/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input(
+                    "image",
+                ),
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the image generation",
+                ),
+                comfy_io.Float.Input(
+                    "image_weight",
+                    default=0.1,
+                    min=0.0,
+                    max=0.98,
+                    step=0.01,
+                    tooltip="Weight of the image; the closer to 1.0, the less the image will be modified.",
+                ),
+                comfy_io.Combo.Input(
+                    "model",
+                    options=[model.value for model in LumaImageModel],
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
+                ),
+            ],
+            outputs=[comfy_io.Image.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": (IO.IMAGE,),
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the image generation",
-                    },
-                ),
-                "image_weight": (
-                    IO.FLOAT,
-                    {
-                        "default": 0.1,
-                        "min": 0.0,
-                        "max": 0.98,
-                        "step": 0.01,
-                        "tooltip": "Weight of the image; the closer to 1.0, the less the image will be modified.",
-                    },
-                ),
-                "model": ([model.value for model in LumaImageModel],),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 0xFFFFFFFFFFFFFFFF,
-                        "control_after_generate": True,
-                        "tooltip": "Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
-                    },
-                ),
-            },
-            "optional": {},
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         prompt: str,
         model: str,
         image: torch.Tensor,
         image_weight: float,
         seed,
-        unique_id: str = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
+        auth_kwargs = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
         # first, upload image
         download_urls = await upload_images_to_comfyapi(
-            image, max_images=1, auth_kwargs=kwargs,
+            image, max_images=1, auth_kwargs=auth_kwargs,
         )
         image_url = download_urls[0]
         # next, make Luma call with download url provided
@@ -401,7 +419,7 @@ class LumaImageModifyNode(ComfyNodeABC):
                     url=image_url, weight=round(max(min(1.0-image_weight, 0.98), 0.0), 2)
                 ),
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_api: LumaGeneration = await operation.execute()
 
@@ -416,88 +434,84 @@ class LumaImageModifyNode(ComfyNodeABC):
             failed_statuses=[LumaState.failed],
             status_extractor=lambda x: x.state,
             result_url_extractor=image_result_url_extractor,
-            node_id=unique_id,
-            auth_kwargs=kwargs,
+            node_id=cls.hidden.unique_id,
+            auth_kwargs=auth_kwargs,
         )
         response_poll = await operation.execute()
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.assets.image) as img_response:
                 img = process_image_response(await img_response.content.read())
-        return (img,)
+        return comfy_io.NodeOutput(img)
 
 
-class LumaTextToVideoGenerationNode(ComfyNodeABC):
+class LumaTextToVideoGenerationNode(comfy_io.ComfyNode):
     """
     Generates videos synchronously based on prompt and output_size.
     """
 
-    RETURN_TYPES = (IO.VIDEO,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/video/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaVideoNode",
+            display_name="Luma Text to Video",
+            category="api node/video/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the video generation",
+                ),
+                comfy_io.Combo.Input(
+                    "model",
+                    options=[model.value for model in LumaVideoModel],
+                ),
+                comfy_io.Combo.Input(
+                    "aspect_ratio",
+                    options=[ratio.value for ratio in LumaAspectRatio],
+                    default=LumaAspectRatio.ratio_16_9,
+                ),
+                comfy_io.Combo.Input(
+                    "resolution",
+                    options=[resolution.value for resolution in LumaVideoOutputResolution],
+                    default=LumaVideoOutputResolution.res_540p,
+                ),
+                comfy_io.Combo.Input(
+                    "duration",
+                    options=[dur.value for dur in LumaVideoModelOutputDuration],
+                ),
+                comfy_io.Boolean.Input(
+                    "loop",
+                    default=False,
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
+                ),
+                comfy_io.Custom(LumaIO.LUMA_CONCEPTS).Input(
+                    "luma_concepts",
+                    tooltip="Optional Camera Concepts to dictate camera motion via the Luma Concepts node.",
+                    optional=True,
+                )
+            ],
+            outputs=[comfy_io.Video.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the video generation",
-                    },
-                ),
-                "model": ([model.value for model in LumaVideoModel],),
-                "aspect_ratio": (
-                    [ratio.value for ratio in LumaAspectRatio],
-                    {
-                        "default": LumaAspectRatio.ratio_16_9,
-                    },
-                ),
-                "resolution": (
-                    [resolution.value for resolution in LumaVideoOutputResolution],
-                    {
-                        "default": LumaVideoOutputResolution.res_540p,
-                    },
-                ),
-                "duration": ([dur.value for dur in LumaVideoModelOutputDuration],),
-                "loop": (
-                    IO.BOOLEAN,
-                    {
-                        "default": False,
-                    },
-                ),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 0xFFFFFFFFFFFFFFFF,
-                        "control_after_generate": True,
-                        "tooltip": "Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
-                    },
-                ),
-            },
-            "optional": {
-                "luma_concepts": (
-                    LumaIO.LUMA_CONCEPTS,
-                    {
-                        "tooltip": "Optional Camera Concepts to dictate camera motion via the Luma Concepts node."
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         prompt: str,
         model: str,
         aspect_ratio: str,
@@ -506,13 +520,15 @@ class LumaTextToVideoGenerationNode(ComfyNodeABC):
         loop: bool,
         seed,
         luma_concepts: LumaConceptChain = None,
-        unique_id: str = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         validate_string(prompt, strip_whitespace=False, min_length=3)
         duration = duration if model != LumaVideoModel.ray_1_6 else None
         resolution = resolution if model != LumaVideoModel.ray_1_6 else None
 
+        auth_kwargs = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
         operation = SynchronousOperation(
             endpoint=ApiEndpoint(
                 path="/proxy/luma/generations",
@@ -529,12 +545,12 @@ class LumaTextToVideoGenerationNode(ComfyNodeABC):
                 loop=loop,
                 concepts=luma_concepts.create_api_model() if luma_concepts else None,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_api: LumaGeneration = await operation.execute()
 
-        if unique_id:
-            PromptServer.instance.send_progress_text(f"Luma video generation started: {response_api.id}", unique_id)
+        if cls.hidden.unique_id:
+            PromptServer.instance.send_progress_text(f"Luma video generation started: {response_api.id}", cls.hidden.unique_id)
 
         operation = PollingOperation(
             poll_endpoint=ApiEndpoint(
@@ -547,90 +563,94 @@ class LumaTextToVideoGenerationNode(ComfyNodeABC):
             failed_statuses=[LumaState.failed],
             status_extractor=lambda x: x.state,
             result_url_extractor=video_result_url_extractor,
-            node_id=unique_id,
+            node_id=cls.hidden.unique_id,
             estimated_duration=LUMA_T2V_AVERAGE_DURATION,
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_poll = await operation.execute()
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.assets.video) as vid_response:
-                return (VideoFromFile(BytesIO(await vid_response.content.read())),)
+                return comfy_io.NodeOutput(VideoFromFile(BytesIO(await vid_response.content.read())))
 
 
-class LumaImageToVideoGenerationNode(ComfyNodeABC):
+class LumaImageToVideoGenerationNode(comfy_io.ComfyNode):
     """
     Generates videos synchronously based on prompt, input images, and output_size.
     """
 
-    RETURN_TYPES = (IO.VIDEO,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/video/Luma"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="LumaImageToVideoNode",
+            display_name="Luma Image to Video",
+            category="api node/video/Luma",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the video generation",
+                ),
+                comfy_io.Combo.Input(
+                    "model",
+                    options=[model.value for model in LumaVideoModel],
+                ),
+                # comfy_io.Combo.Input(
+                #     "aspect_ratio",
+                #     options=[ratio.value for ratio in LumaAspectRatio],
+                #     default=LumaAspectRatio.ratio_16_9,
+                # ),
+                comfy_io.Combo.Input(
+                    "resolution",
+                    options=[resolution.value for resolution in LumaVideoOutputResolution],
+                    default=LumaVideoOutputResolution.res_540p,
+                ),
+                comfy_io.Combo.Input(
+                    "duration",
+                    options=[dur.value for dur in LumaVideoModelOutputDuration],
+                ),
+                comfy_io.Boolean.Input(
+                    "loop",
+                    default=False,
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
+                ),
+                comfy_io.Image.Input(
+                    "first_image",
+                    tooltip="First frame of generated video.",
+                    optional=True,
+                ),
+                comfy_io.Image.Input(
+                    "last_image",
+                    tooltip="Last frame of generated video.",
+                    optional=True,
+                ),
+                comfy_io.Custom(LumaIO.LUMA_CONCEPTS).Input(
+                    "luma_concepts",
+                    tooltip="Optional Camera Concepts to dictate camera motion via the Luma Concepts node.",
+                    optional=True,
+                )
+            ],
+            outputs=[comfy_io.Video.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the video generation",
-                    },
-                ),
-                "model": ([model.value for model in LumaVideoModel],),
-                # "aspect_ratio": ([ratio.value for ratio in LumaAspectRatio], {
-                #     "default": LumaAspectRatio.ratio_16_9,
-                # }),
-                "resolution": (
-                    [resolution.value for resolution in LumaVideoOutputResolution],
-                    {
-                        "default": LumaVideoOutputResolution.res_540p,
-                    },
-                ),
-                "duration": ([dur.value for dur in LumaVideoModelOutputDuration],),
-                "loop": (
-                    IO.BOOLEAN,
-                    {
-                        "default": False,
-                    },
-                ),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 0xFFFFFFFFFFFFFFFF,
-                        "control_after_generate": True,
-                        "tooltip": "Seed to determine if node should re-run; actual results are nondeterministic regardless of seed.",
-                    },
-                ),
-            },
-            "optional": {
-                "first_image": (
-                    IO.IMAGE,
-                    {"tooltip": "First frame of generated video."},
-                ),
-                "last_image": (IO.IMAGE, {"tooltip": "Last frame of generated video."}),
-                "luma_concepts": (
-                    LumaIO.LUMA_CONCEPTS,
-                    {
-                        "tooltip": "Optional Camera Concepts to dictate camera motion via the Luma Concepts node."
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         prompt: str,
         model: str,
         resolution: str,
@@ -640,14 +660,16 @@ class LumaImageToVideoGenerationNode(ComfyNodeABC):
         first_image: torch.Tensor = None,
         last_image: torch.Tensor = None,
         luma_concepts: LumaConceptChain = None,
-        unique_id: str = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         if first_image is None and last_image is None:
             raise Exception(
                 "At least one of first_image and last_image requires an input."
             )
-        keyframes = await self._convert_to_keyframes(first_image, last_image, auth_kwargs=kwargs)
+        auth_kwargs = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
+        keyframes = await cls._convert_to_keyframes(first_image, last_image, auth_kwargs=auth_kwargs)
         duration = duration if model != LumaVideoModel.ray_1_6 else None
         resolution = resolution if model != LumaVideoModel.ray_1_6 else None
 
@@ -668,12 +690,12 @@ class LumaImageToVideoGenerationNode(ComfyNodeABC):
                 keyframes=keyframes,
                 concepts=luma_concepts.create_api_model() if luma_concepts else None,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_api: LumaGeneration = await operation.execute()
 
-        if unique_id:
-            PromptServer.instance.send_progress_text(f"Luma video generation started: {response_api.id}", unique_id)
+        if cls.hidden.unique_id:
+            PromptServer.instance.send_progress_text(f"Luma video generation started: {response_api.id}", cls.hidden.unique_id)
 
         operation = PollingOperation(
             poll_endpoint=ApiEndpoint(
@@ -686,18 +708,19 @@ class LumaImageToVideoGenerationNode(ComfyNodeABC):
             failed_statuses=[LumaState.failed],
             status_extractor=lambda x: x.state,
             result_url_extractor=video_result_url_extractor,
-            node_id=unique_id,
+            node_id=cls.hidden.unique_id,
             estimated_duration=LUMA_I2V_AVERAGE_DURATION,
-            auth_kwargs=kwargs,
+            auth_kwargs=auth_kwargs,
         )
         response_poll = await operation.execute()
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.assets.video) as vid_response:
-                return (VideoFromFile(BytesIO(await vid_response.content.read())),)
+                return comfy_io.NodeOutput(VideoFromFile(BytesIO(await vid_response.content.read())))
 
+    @classmethod
     async def _convert_to_keyframes(
-        self,
+        cls,
         first_image: torch.Tensor = None,
         last_image: torch.Tensor = None,
         auth_kwargs: Optional[dict[str,str]] = None,
@@ -719,23 +742,18 @@ class LumaImageToVideoGenerationNode(ComfyNodeABC):
         return LumaKeyframes(frame0=frame0, frame1=frame1)
 
 
-# A dictionary that contains all nodes you want to export with their names
-# NOTE: names should be globally unique
-NODE_CLASS_MAPPINGS = {
-    "LumaImageNode": LumaImageGenerationNode,
-    "LumaImageModifyNode": LumaImageModifyNode,
-    "LumaVideoNode": LumaTextToVideoGenerationNode,
-    "LumaImageToVideoNode": LumaImageToVideoGenerationNode,
-    "LumaReferenceNode": LumaReferenceNode,
-    "LumaConceptsNode": LumaConceptsNode,
-}
+class LumaExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
+        return [
+            LumaImageGenerationNode,
+            LumaImageModifyNode,
+            LumaTextToVideoGenerationNode,
+            LumaImageToVideoGenerationNode,
+            LumaReferenceNode,
+            LumaConceptsNode,
+        ]
 
-# A dictionary that contains the friendly/humanly readable titles for the nodes
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "LumaImageNode": "Luma Text to Image",
-    "LumaImageModifyNode": "Luma Image to Image",
-    "LumaVideoNode": "Luma Text to Video",
-    "LumaImageToVideoNode": "Luma Image to Video",
-    "LumaReferenceNode": "Luma Reference",
-    "LumaConceptsNode": "Luma Concepts",
-}
+
+async def comfy_entrypoint() -> LumaExtension:
+    return LumaExtension()

comfy_api_nodes/nodes_moonvalley.py

@@ -2,11 +2,7 @@ import logging
 from typing import Any, Callable, Optional, TypeVar
 import torch
 from typing_extensions import override
-from comfy_api_nodes.util.validation_utils import (
-    get_image_dimensions,
-    validate_image_dimensions,
-)
-
+from comfy_api_nodes.util.validation_utils import validate_image_dimensions
 
 from comfy_api_nodes.apis import (
     MoonvalleyTextToVideoRequest,
@@ -132,47 +128,6 @@ def validate_prompts(
     return True
 
 
-def validate_input_media(width, height, with_frame_conditioning, num_frames_in=None):
-    # inference validation
-    # T = num_frames
-    # in all cases, the following must be true: T divisible by 16 and H,W by 8. in addition...
-    # with image conditioning: H*W must be divisible by 8192
-    # without image conditioning: T divisible by 32
-    if num_frames_in and not num_frames_in % 16 == 0:
-        return False, ("The input video total frame count must be divisible by 16!")
-
-    if height % 8 != 0 or width % 8 != 0:
-        return False, (
-            f"Height ({height}) and width ({width}) must be " "divisible by 8"
-        )
-
-    if with_frame_conditioning:
-        if (height * width) % 8192 != 0:
-            return False, (
-                f"Height * width ({height * width}) must be "
-                "divisible by 8192 for frame conditioning"
-            )
-    else:
-        if num_frames_in and not num_frames_in % 32 == 0:
-            return False, ("The input video total frame count must be divisible by 32!")
-
-
-def validate_input_image(
-    image: torch.Tensor, with_frame_conditioning: bool = False
-) -> None:
-    """
-    Validates the input image adheres to the expectations of the API:
-    - The image resolution should not be less than 300*300px
-    - The aspect ratio of the image should be between 1:2.5 ~ 2.5:1
-
-    """
-    height, width = get_image_dimensions(image)
-    validate_input_media(width, height, with_frame_conditioning)
-    validate_image_dimensions(
-        image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH
-    )
-
-
 def validate_video_to_video_input(video: VideoInput) -> VideoInput:
     """
     Validates and processes video input for Moonvalley Video-to-Video generation.
@@ -499,7 +454,7 @@ class MoonvalleyImg2VideoNode(comfy_io.ComfyNode):
         seed: int,
         steps: int,
     ) -> comfy_io.NodeOutput:
-        validate_input_image(image, True)
+        validate_image_dimensions(image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH)
         validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
         width_height = parse_width_height_from_res(resolution)
 

comfy_api_nodes/nodes_pixverse.py

@@ -1,5 +1,7 @@
 from inspect import cleandoc
 from typing import Optional
+from typing_extensions import override
+from io import BytesIO
 from comfy_api_nodes.apis.pixverse_api import (
     PixverseTextVideoRequest,
     PixverseImageVideoRequest,
@@ -26,12 +28,11 @@ from comfy_api_nodes.apinode_utils import (
     tensor_to_bytesio,
     validate_string,
 )
-from comfy.comfy_types.node_typing import IO, ComfyNodeABC
 from comfy_api.input_impl import VideoFromFile
+from comfy_api.latest import ComfyExtension, io as comfy_io
 
 import torch
 import aiohttp
-from io import BytesIO
 
 
 AVERAGE_DURATION_T2V = 32
@@ -72,100 +73,101 @@ async def upload_image_to_pixverse(image: torch.Tensor, auth_kwargs=None):
     return response_upload.Resp.img_id
 
 
-class PixverseTemplateNode:
+class PixverseTemplateNode(comfy_io.ComfyNode):
     """
     Select template for PixVerse Video generation.
     """
 
-    RETURN_TYPES = (PixverseIO.TEMPLATE,)
-    RETURN_NAMES = ("pixverse_template",)
-    FUNCTION = "create_template"
-    CATEGORY = "api node/video/PixVerse"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="PixverseTemplateNode",
+            display_name="PixVerse Template",
+            category="api node/video/PixVerse",
+            inputs=[
+                comfy_io.Combo.Input("template", options=[list(pixverse_templates.keys())]),
+            ],
+            outputs=[comfy_io.Custom(PixverseIO.TEMPLATE).Output(display_name="pixverse_template")],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "template": (list(pixverse_templates.keys()),),
-            }
-        }
-
-    def create_template(self, template: str):
+    def execute(cls, template: str) -> comfy_io.NodeOutput:
         template_id = pixverse_templates.get(template, None)
         if template_id is None:
             raise Exception(f"Template '{template}' is not recognized.")
         # just return the integer
-        return (template_id,)
+        return comfy_io.NodeOutput(template_id)
 
 
-class PixverseTextToVideoNode(ComfyNodeABC):
+class PixverseTextToVideoNode(comfy_io.ComfyNode):
     """
     Generates videos based on prompt and output_size.
     """
 
-    RETURN_TYPES = (IO.VIDEO,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/video/PixVerse"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="PixverseTextToVideoNode",
+            display_name="PixVerse Text to Video",
+            category="api node/video/PixVerse",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the video generation",
+                ),
+                comfy_io.Combo.Input(
+                    "aspect_ratio",
+                    options=[ratio.value for ratio in PixverseAspectRatio],
+                ),
+                comfy_io.Combo.Input(
+                    "quality",
+                    options=[resolution.value for resolution in PixverseQuality],
+                    default=PixverseQuality.res_540p,
+                ),
+                comfy_io.Combo.Input(
+                    "duration_seconds",
+                    options=[dur.value for dur in PixverseDuration],
+                ),
+                comfy_io.Combo.Input(
+                    "motion_mode",
+                    options=[mode.value for mode in PixverseMotionMode],
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed for video generation.",
+                ),
+                comfy_io.String.Input(
+                    "negative_prompt",
+                    default="",
+                    force_input=True,
+                    tooltip="An optional text description of undesired elements on an image.",
+                    optional=True,
+                ),
+                comfy_io.Custom(PixverseIO.TEMPLATE).Input(
+                    "pixverse_template",
+                    tooltip="An optional template to influence style of generation, created by the PixVerse Template node.",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Video.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the video generation",
-                    },
-                ),
-                "aspect_ratio": ([ratio.value for ratio in PixverseAspectRatio],),
-                "quality": (
-                    [resolution.value for resolution in PixverseQuality],
-                    {
-                        "default": PixverseQuality.res_540p,
-                    },
-                ),
-                "duration_seconds": ([dur.value for dur in PixverseDuration],),
-                "motion_mode": ([mode.value for mode in PixverseMotionMode],),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 2147483647,
-                        "control_after_generate": True,
-                        "tooltip": "Seed for video generation.",
-                    },
-                ),
-            },
-            "optional": {
-                "negative_prompt": (
-                    IO.STRING,
-                    {
-                        "default": "",
-                        "forceInput": True,
-                        "tooltip": "An optional text description of undesired elements on an image.",
-                    },
-                ),
-                "pixverse_template": (
-                    PixverseIO.TEMPLATE,
-                    {
-                        "tooltip": "An optional template to influence style of generation, created by the PixVerse Template node."
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         prompt: str,
         aspect_ratio: str,
         quality: str,
@@ -174,9 +176,7 @@ class PixverseTextToVideoNode(ComfyNodeABC):
         seed,
         negative_prompt: str = None,
         pixverse_template: int = None,
-        unique_id: Optional[str] = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         validate_string(prompt, strip_whitespace=False)
         # 1080p is limited to 5 seconds duration
         # only normal motion_mode supported for 1080p or for non-5 second duration
@@ -186,6 +186,10 @@ class PixverseTextToVideoNode(ComfyNodeABC):
         elif duration_seconds != PixverseDuration.dur_5:
             motion_mode = PixverseMotionMode.normal
 
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
         operation = SynchronousOperation(
             endpoint=ApiEndpoint(
                 path="/proxy/pixverse/video/text/generate",
@@ -203,7 +207,7 @@ class PixverseTextToVideoNode(ComfyNodeABC):
                 template_id=pixverse_template,
                 seed=seed,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth,
         )
         response_api = await operation.execute()
 
@@ -224,8 +228,8 @@ class PixverseTextToVideoNode(ComfyNodeABC):
                 PixverseStatus.deleted,
             ],
             status_extractor=lambda x: x.Resp.status,
-            auth_kwargs=kwargs,
-            node_id=unique_id,
+            auth_kwargs=auth,
+            node_id=cls.hidden.unique_id,
             result_url_extractor=get_video_url_from_response,
             estimated_duration=AVERAGE_DURATION_T2V,
         )
@@ -233,77 +237,75 @@ class PixverseTextToVideoNode(ComfyNodeABC):
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.Resp.url) as vid_response:
-                return (VideoFromFile(BytesIO(await vid_response.content.read())),)
+                return comfy_io.NodeOutput(VideoFromFile(BytesIO(await vid_response.content.read())))
 
 
-class PixverseImageToVideoNode(ComfyNodeABC):
+class PixverseImageToVideoNode(comfy_io.ComfyNode):
     """
     Generates videos based on prompt and output_size.
     """
 
-    RETURN_TYPES = (IO.VIDEO,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/video/PixVerse"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="PixverseImageToVideoNode",
+            display_name="PixVerse Image to Video",
+            category="api node/video/PixVerse",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("image"),
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the video generation",
+                ),
+                comfy_io.Combo.Input(
+                    "quality",
+                    options=[resolution.value for resolution in PixverseQuality],
+                    default=PixverseQuality.res_540p,
+                ),
+                comfy_io.Combo.Input(
+                    "duration_seconds",
+                    options=[dur.value for dur in PixverseDuration],
+                ),
+                comfy_io.Combo.Input(
+                    "motion_mode",
+                    options=[mode.value for mode in PixverseMotionMode],
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed for video generation.",
+                ),
+                comfy_io.String.Input(
+                    "negative_prompt",
+                    default="",
+                    force_input=True,
+                    tooltip="An optional text description of undesired elements on an image.",
+                    optional=True,
+                ),
+                comfy_io.Custom(PixverseIO.TEMPLATE).Input(
+                    "pixverse_template",
+                    tooltip="An optional template to influence style of generation, created by the PixVerse Template node.",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Video.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": (IO.IMAGE,),
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the video generation",
-                    },
-                ),
-                "quality": (
-                    [resolution.value for resolution in PixverseQuality],
-                    {
-                        "default": PixverseQuality.res_540p,
-                    },
-                ),
-                "duration_seconds": ([dur.value for dur in PixverseDuration],),
-                "motion_mode": ([mode.value for mode in PixverseMotionMode],),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 2147483647,
-                        "control_after_generate": True,
-                        "tooltip": "Seed for video generation.",
-                    },
-                ),
-            },
-            "optional": {
-                "negative_prompt": (
-                    IO.STRING,
-                    {
-                        "default": "",
-                        "forceInput": True,
-                        "tooltip": "An optional text description of undesired elements on an image.",
-                    },
-                ),
-                "pixverse_template": (
-                    PixverseIO.TEMPLATE,
-                    {
-                        "tooltip": "An optional template to influence style of generation, created by the PixVerse Template node."
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         image: torch.Tensor,
         prompt: str,
         quality: str,
@@ -312,11 +314,13 @@ class PixverseImageToVideoNode(ComfyNodeABC):
         seed,
         negative_prompt: str = None,
         pixverse_template: int = None,
-        unique_id: Optional[str] = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         validate_string(prompt, strip_whitespace=False)
-        img_id = await upload_image_to_pixverse(image, auth_kwargs=kwargs)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
+        img_id = await upload_image_to_pixverse(image, auth_kwargs=auth)
 
         # 1080p is limited to 5 seconds duration
         # only normal motion_mode supported for 1080p or for non-5 second duration
@@ -343,7 +347,7 @@ class PixverseImageToVideoNode(ComfyNodeABC):
                 template_id=pixverse_template,
                 seed=seed,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth,
         )
         response_api = await operation.execute()
 
@@ -364,8 +368,8 @@ class PixverseImageToVideoNode(ComfyNodeABC):
                 PixverseStatus.deleted,
             ],
             status_extractor=lambda x: x.Resp.status,
-            auth_kwargs=kwargs,
-            node_id=unique_id,
+            auth_kwargs=auth,
+            node_id=cls.hidden.unique_id,
             result_url_extractor=get_video_url_from_response,
             estimated_duration=AVERAGE_DURATION_I2V,
         )
@@ -373,72 +377,71 @@ class PixverseImageToVideoNode(ComfyNodeABC):
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.Resp.url) as vid_response:
-                return (VideoFromFile(BytesIO(await vid_response.content.read())),)
+                return comfy_io.NodeOutput(VideoFromFile(BytesIO(await vid_response.content.read())))
 
 
-class PixverseTransitionVideoNode(ComfyNodeABC):
+class PixverseTransitionVideoNode(comfy_io.ComfyNode):
     """
     Generates videos based on prompt and output_size.
     """
 
-    RETURN_TYPES = (IO.VIDEO,)
-    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
-    FUNCTION = "api_call"
-    API_NODE = True
-    CATEGORY = "api node/video/PixVerse"
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="PixverseTransitionVideoNode",
+            display_name="PixVerse Transition Video",
+            category="api node/video/PixVerse",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("first_frame"),
+                comfy_io.Image.Input("last_frame"),
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt for the video generation",
+                ),
+                comfy_io.Combo.Input(
+                    "quality",
+                    options=[resolution.value for resolution in PixverseQuality],
+                    default=PixverseQuality.res_540p,
+                ),
+                comfy_io.Combo.Input(
+                    "duration_seconds",
+                    options=[dur.value for dur in PixverseDuration],
+                ),
+                comfy_io.Combo.Input(
+                    "motion_mode",
+                    options=[mode.value for mode in PixverseMotionMode],
+                ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    control_after_generate=True,
+                    tooltip="Seed for video generation.",
+                ),
+                comfy_io.String.Input(
+                    "negative_prompt",
+                    default="",
+                    force_input=True,
+                    tooltip="An optional text description of undesired elements on an image.",
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.Video.Output()],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "first_frame": (IO.IMAGE,),
-                "last_frame": (IO.IMAGE,),
-                "prompt": (
-                    IO.STRING,
-                    {
-                        "multiline": True,
-                        "default": "",
-                        "tooltip": "Prompt for the video generation",
-                    },
-                ),
-                "quality": (
-                    [resolution.value for resolution in PixverseQuality],
-                    {
-                        "default": PixverseQuality.res_540p,
-                    },
-                ),
-                "duration_seconds": ([dur.value for dur in PixverseDuration],),
-                "motion_mode": ([mode.value for mode in PixverseMotionMode],),
-                "seed": (
-                    IO.INT,
-                    {
-                        "default": 0,
-                        "min": 0,
-                        "max": 2147483647,
-                        "control_after_generate": True,
-                        "tooltip": "Seed for video generation.",
-                    },
-                ),
-            },
-            "optional": {
-                "negative_prompt": (
-                    IO.STRING,
-                    {
-                        "default": "",
-                        "forceInput": True,
-                        "tooltip": "An optional text description of undesired elements on an image.",
-                    },
-                ),
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-                "unique_id": "UNIQUE_ID",
-            },
-        }
-
-    async def api_call(
-        self,
+    async def execute(
+        cls,
         first_frame: torch.Tensor,
         last_frame: torch.Tensor,
         prompt: str,
@@ -447,12 +450,14 @@ class PixverseTransitionVideoNode(ComfyNodeABC):
         motion_mode: str,
         seed,
         negative_prompt: str = None,
-        unique_id: Optional[str] = None,
-        **kwargs,
-    ):
+    ) -> comfy_io.NodeOutput:
         validate_string(prompt, strip_whitespace=False)
-        first_frame_id = await upload_image_to_pixverse(first_frame, auth_kwargs=kwargs)
-        last_frame_id = await upload_image_to_pixverse(last_frame, auth_kwargs=kwargs)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
+        first_frame_id = await upload_image_to_pixverse(first_frame, auth_kwargs=auth)
+        last_frame_id = await upload_image_to_pixverse(last_frame, auth_kwargs=auth)
 
         # 1080p is limited to 5 seconds duration
         # only normal motion_mode supported for 1080p or for non-5 second duration
@@ -479,7 +484,7 @@ class PixverseTransitionVideoNode(ComfyNodeABC):
                 negative_prompt=negative_prompt if negative_prompt else None,
                 seed=seed,
             ),
-            auth_kwargs=kwargs,
+            auth_kwargs=auth,
         )
         response_api = await operation.execute()
 
@@ -500,8 +505,8 @@ class PixverseTransitionVideoNode(ComfyNodeABC):
                 PixverseStatus.deleted,
             ],
             status_extractor=lambda x: x.Resp.status,
-            auth_kwargs=kwargs,
-            node_id=unique_id,
+            auth_kwargs=auth,
+            node_id=cls.hidden.unique_id,
             result_url_extractor=get_video_url_from_response,
             estimated_duration=AVERAGE_DURATION_T2V,
         )
@@ -509,19 +514,19 @@ class PixverseTransitionVideoNode(ComfyNodeABC):
 
         async with aiohttp.ClientSession() as session:
             async with session.get(response_poll.Resp.url) as vid_response:
-                return (VideoFromFile(BytesIO(await vid_response.content.read())),)
+                return comfy_io.NodeOutput(VideoFromFile(BytesIO(await vid_response.content.read())))
 
 
-NODE_CLASS_MAPPINGS = {
-    "PixverseTextToVideoNode": PixverseTextToVideoNode,
-    "PixverseImageToVideoNode": PixverseImageToVideoNode,
-    "PixverseTransitionVideoNode": PixverseTransitionVideoNode,
-    "PixverseTemplateNode": PixverseTemplateNode,
-}
+class PixVerseExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
+        return [
+            PixverseTextToVideoNode,
+            PixverseImageToVideoNode,
+            PixverseTransitionVideoNode,
+            PixverseTemplateNode,
+        ]
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "PixverseTextToVideoNode": "PixVerse Text to Video",
-    "PixverseImageToVideoNode": "PixVerse Image to Video",
-    "PixverseTransitionVideoNode": "PixVerse Transition Video",
-    "PixverseTemplateNode": "PixVerse Template",
-}
+
+async def comfy_entrypoint() -> PixVerseExtension:
+    return PixVerseExtension()

comfy_api_nodes/nodes_recraft.py

@@ -38,48 +38,48 @@ from PIL import UnidentifiedImageError
 
 
 async def handle_recraft_file_request(
-        image: torch.Tensor,
-        path: str,
-        mask: torch.Tensor=None,
-        total_pixels=4096*4096,
-        timeout=1024,
-        request=None,
-        auth_kwargs: dict[str,str] = None,
-    ) -> list[BytesIO]:
-        """
-        Handle sending common Recraft file-only request to get back file bytes.
-        """
-        if request is None:
-            request = EmptyRequest()
+    image: torch.Tensor,
+    path: str,
+    mask: torch.Tensor=None,
+    total_pixels=4096*4096,
+    timeout=1024,
+    request=None,
+    auth_kwargs: dict[str,str] = None,
+) -> list[BytesIO]:
+    """
+    Handle sending common Recraft file-only request to get back file bytes.
+    """
+    if request is None:
+        request = EmptyRequest()
 
-        files = {
-            'image': tensor_to_bytesio(image, total_pixels=total_pixels).read()
-        }
-        if mask is not None:
-            files['mask'] = tensor_to_bytesio(mask, total_pixels=total_pixels).read()
+    files = {
+        'image': tensor_to_bytesio(image, total_pixels=total_pixels).read()
+    }
+    if mask is not None:
+        files['mask'] = tensor_to_bytesio(mask, total_pixels=total_pixels).read()
 
-        operation = SynchronousOperation(
-            endpoint=ApiEndpoint(
-                path=path,
-                method=HttpMethod.POST,
-                request_model=type(request),
-                response_model=RecraftImageGenerationResponse,
-            ),
-            request=request,
-            files=files,
-            content_type="multipart/form-data",
-            auth_kwargs=auth_kwargs,
-            multipart_parser=recraft_multipart_parser,
-        )
-        response: RecraftImageGenerationResponse = await operation.execute()
-        all_bytesio = []
-        if response.image is not None:
-            all_bytesio.append(await download_url_to_bytesio(response.image.url, timeout=timeout))
-        else:
-            for data in response.data:
-                all_bytesio.append(await download_url_to_bytesio(data.url, timeout=timeout))
+    operation = SynchronousOperation(
+        endpoint=ApiEndpoint(
+            path=path,
+            method=HttpMethod.POST,
+            request_model=type(request),
+            response_model=RecraftImageGenerationResponse,
+        ),
+        request=request,
+        files=files,
+        content_type="multipart/form-data",
+        auth_kwargs=auth_kwargs,
+        multipart_parser=recraft_multipart_parser,
+    )
+    response: RecraftImageGenerationResponse = await operation.execute()
+    all_bytesio = []
+    if response.image is not None:
+        all_bytesio.append(await download_url_to_bytesio(response.image.url, timeout=timeout))
+    else:
+        for data in response.data:
+            all_bytesio.append(await download_url_to_bytesio(data.url, timeout=timeout))
 
-        return all_bytesio
+    return all_bytesio
 
 
 def recraft_multipart_parser(data, parent_key=None, formatter: callable=None, converted_to_check: list[list]=None, is_list=False) -> dict:

comfy_api_nodes/nodes_rodin.py

@@ -7,15 +7,15 @@ Rodin API docs: https://developer.hyper3d.ai/
 
 from __future__ import annotations
 from inspect import cleandoc
-from comfy.comfy_types.node_typing import IO
 import folder_paths as comfy_paths
 import aiohttp
 import os
-import datetime
 import asyncio
-import io
 import logging
 import math
+from typing import Optional
+from io import BytesIO
+from typing_extensions import override
 from PIL import Image
 from comfy_api_nodes.apis.rodin_api import (
     Rodin3DGenerateRequest,
@@ -32,444 +32,548 @@ from comfy_api_nodes.apis.client import (
     SynchronousOperation,
     PollingOperation,
 )
+from comfy_api.latest import ComfyExtension, io as comfy_io
 
 
-COMMON_PARAMETERS = {
-    "Seed": (
-        IO.INT,
-        {
-            "default":0,
-            "min":0,
-            "max":65535,
-            "display":"number"
-        }
+COMMON_PARAMETERS = [
+    comfy_io.Int.Input(
+        "Seed",
+        default=0,
+        min=0,
+        max=65535,
+        display_mode=comfy_io.NumberDisplay.number,
+        optional=True,
     ),
-    "Material_Type": (
-        IO.COMBO,
-        {
-            "options": ["PBR", "Shaded"],
-            "default": "PBR"
-        }
+    comfy_io.Combo.Input("Material_Type", options=["PBR", "Shaded"], default="PBR", optional=True),
+    comfy_io.Combo.Input(
+        "Polygon_count",
+        options=["4K-Quad", "8K-Quad", "18K-Quad", "50K-Quad", "200K-Triangle"],
+        default="18K-Quad",
+        optional=True,
     ),
-    "Polygon_count": (
-        IO.COMBO,
-        {
-            "options": ["4K-Quad", "8K-Quad", "18K-Quad", "50K-Quad", "200K-Triangle"],
-            "default": "18K-Quad"
-        }
+]
+
+
+def get_quality_mode(poly_count):
+    polycount = poly_count.split("-")
+    poly = polycount[1]
+    count = polycount[0]
+    if poly == "Triangle":
+        mesh_mode = "Raw"
+    elif poly == "Quad":
+        mesh_mode = "Quad"
+    else:
+        mesh_mode = "Quad"
+
+    if count == "4K":
+        quality_override = 4000
+    elif count == "8K":
+        quality_override = 8000
+    elif count == "18K":
+        quality_override = 18000
+    elif count == "50K":
+        quality_override = 50000
+    elif count == "2K":
+        quality_override = 2000
+    elif count == "20K":
+        quality_override = 20000
+    elif count == "150K":
+        quality_override = 150000
+    elif count == "500K":
+        quality_override = 500000
+    else:
+        quality_override = 18000
+
+    return mesh_mode, quality_override
+
+
+def tensor_to_filelike(tensor, max_pixels: int = 2048*2048):
+    """
+    Converts a PyTorch tensor to a file-like object.
+
+    Args:
+    - tensor (torch.Tensor): A tensor representing an image of shape (H, W, C)
+      where C is the number of channels (3 for RGB), H is height, and W is width.
+
+    Returns:
+    - io.BytesIO: A file-like object containing the image data.
+    """
+    array = tensor.cpu().numpy()
+    array = (array * 255).astype('uint8')
+    image = Image.fromarray(array, 'RGB')
+
+    original_width, original_height = image.size
+    original_pixels = original_width * original_height
+    if original_pixels > max_pixels:
+        scale = math.sqrt(max_pixels / original_pixels)
+        new_width = int(original_width * scale)
+        new_height = int(original_height * scale)
+    else:
+        new_width, new_height = original_width, original_height
+
+    if new_width != original_width or new_height != original_height:
+        image = image.resize((new_width, new_height), Image.Resampling.LANCZOS)
+
+    img_byte_arr = BytesIO()
+    image.save(img_byte_arr, format='PNG')  # PNG is used for lossless compression
+    img_byte_arr.seek(0)
+    return img_byte_arr
+
+
+async def create_generate_task(
+    images=None,
+    seed=1,
+    material="PBR",
+    quality_override=18000,
+    tier="Regular",
+    mesh_mode="Quad",
+    TAPose = False,
+    auth_kwargs: Optional[dict[str, str]] = None,
+):
+    if images is None:
+        raise Exception("Rodin 3D generate requires at least 1 image.")
+    if len(images) > 5:
+        raise Exception("Rodin 3D generate requires up to 5 image.")
+
+    path = "/proxy/rodin/api/v2/rodin"
+    operation = SynchronousOperation(
+        endpoint=ApiEndpoint(
+            path=path,
+            method=HttpMethod.POST,
+            request_model=Rodin3DGenerateRequest,
+            response_model=Rodin3DGenerateResponse,
+        ),
+        request=Rodin3DGenerateRequest(
+            seed=seed,
+            tier=tier,
+            material=material,
+            quality_override=quality_override,
+            mesh_mode=mesh_mode,
+            TAPose=TAPose,
+        ),
+        files=[
+            (
+                "images",
+                open(image, "rb") if isinstance(image, str) else tensor_to_filelike(image)
+            )
+            for image in images if image is not None
+        ],
+        content_type="multipart/form-data",
+        auth_kwargs=auth_kwargs,
     )
-}
 
-def create_task_error(response: Rodin3DGenerateResponse):
-    """Check if the response has error"""
-    return hasattr(response, "error")
+    response = await operation.execute()
+
+    if hasattr(response, "error"):
+        error_message = f"Rodin3D Create 3D generate Task Failed. Message: {response.message}, error: {response.error}"
+        logging.error(error_message)
+        raise Exception(error_message)
+
+    logging.info("[ Rodin3D API - Submit Jobs ] Submit Generate Task Success!")
+    subscription_key = response.jobs.subscription_key
+    task_uuid = response.uuid
+    logging.info(f"[ Rodin3D API - Submit Jobs ] UUID: {task_uuid}")
+    return task_uuid, subscription_key
 
 
-class Rodin3DAPI:
-    """
-    Generate 3D Assets using Rodin API
-    """
-    RETURN_TYPES = (IO.STRING,)
-    RETURN_NAMES = ("3D Model Path",)
-    CATEGORY = "api node/3d/Rodin"
-    DESCRIPTION = cleandoc(__doc__ or "")
-    FUNCTION = "api_call"
-    API_NODE = True
-
-    def tensor_to_filelike(self, tensor, max_pixels: int = 2048*2048):
-        """
-        Converts a PyTorch tensor to a file-like object.
-
-        Args:
-        - tensor (torch.Tensor): A tensor representing an image of shape (H, W, C)
-          where C is the number of channels (3 for RGB), H is height, and W is width.
-
-        Returns:
-        - io.BytesIO: A file-like object containing the image data.
-        """
-        array = tensor.cpu().numpy()
-        array = (array * 255).astype('uint8')
-        image = Image.fromarray(array, 'RGB')
-
-        original_width, original_height = image.size
-        original_pixels = original_width * original_height
-        if original_pixels > max_pixels:
-            scale = math.sqrt(max_pixels / original_pixels)
-            new_width = int(original_width * scale)
-            new_height = int(original_height * scale)
-        else:
-            new_width, new_height = original_width, original_height
-
-        if new_width != original_width or new_height != original_height:
-            image = image.resize((new_width, new_height), Image.Resampling.LANCZOS)
-
-        img_byte_arr = io.BytesIO()
-        image.save(img_byte_arr, format='PNG')  # PNG is used for lossless compression
-        img_byte_arr.seek(0)
-        return img_byte_arr
-
-    def check_rodin_status(self, response: Rodin3DCheckStatusResponse) -> str:
-        has_failed = any(job.status == JobStatus.Failed for job in response.jobs)
-        all_done = all(job.status == JobStatus.Done for job in response.jobs)
-        status_list = [str(job.status) for job in response.jobs]
-        logging.info(f"[ Rodin3D API - CheckStatus ] Generate Status: {status_list}")
-        if has_failed:
-            logging.error(f"[ Rodin3D API - CheckStatus ] Generate Failed: {status_list}, Please try again.")
-            raise Exception("[ Rodin3D API ] Generate Failed, Please Try again.")
-        elif all_done:
-            return "DONE"
-        else:
-            return "Generating"
-
-    async def create_generate_task(self, images=None, seed=1, material="PBR", quality="medium", tier="Regular", mesh_mode="Quad", **kwargs):
-        if images is None:
-            raise Exception("Rodin 3D generate requires at least 1 image.")
-        if len(images) >= 5:
-            raise Exception("Rodin 3D generate requires up to 5 image.")
-
-        path = "/proxy/rodin/api/v2/rodin"
-        operation = SynchronousOperation(
-            endpoint=ApiEndpoint(
-                path=path,
-                method=HttpMethod.POST,
-                request_model=Rodin3DGenerateRequest,
-                response_model=Rodin3DGenerateResponse,
-            ),
-            request=Rodin3DGenerateRequest(
-                seed=seed,
-                tier=tier,
-                material=material,
-                quality=quality,
-                mesh_mode=mesh_mode
-            ),
-            files=[
-                (
-                    "images",
-                    open(image, "rb") if isinstance(image, str) else self.tensor_to_filelike(image)
-                )
-                for image in images if image is not None
-            ],
-            content_type = "multipart/form-data",
-            auth_kwargs=kwargs,
-        )
-
-        response = await operation.execute()
-
-        if create_task_error(response):
-            error_message = f"Rodin3D Create 3D generate Task Failed. Message: {response.message}, error: {response.error}"
-            logging.error(error_message)
-            raise Exception(error_message)
-
-        logging.info("[ Rodin3D API - Submit Jobs ] Submit Generate Task Success!")
-        subscription_key = response.jobs.subscription_key
-        task_uuid = response.uuid
-        logging.info(f"[ Rodin3D API - Submit Jobs ] UUID: {task_uuid}")
-        return task_uuid, subscription_key
-
-    async def poll_for_task_status(self, subscription_key, **kwargs) -> Rodin3DCheckStatusResponse:
-
-        path = "/proxy/rodin/api/v2/status"
-
-        poll_operation = PollingOperation(
-            poll_endpoint=ApiEndpoint(
-                path = path,
-                method=HttpMethod.POST,
-                request_model=Rodin3DCheckStatusRequest,
-                response_model=Rodin3DCheckStatusResponse,
-            ),
-            request=Rodin3DCheckStatusRequest(
-                subscription_key = subscription_key
-            ),
-            completed_statuses=["DONE"],
-            failed_statuses=["FAILED"],
-            status_extractor=self.check_rodin_status,
-            poll_interval=3.0,
-            auth_kwargs=kwargs,
-        )
-
-        logging.info("[ Rodin3D API - CheckStatus ] Generate Start!")
-
-        return await poll_operation.execute()
-
-    async def get_rodin_download_list(self, uuid, **kwargs) -> Rodin3DDownloadResponse:
-        logging.info("[ Rodin3D API - Downloading ] Generate Successfully!")
-
-        path = "/proxy/rodin/api/v2/download"
-        operation = SynchronousOperation(
-            endpoint=ApiEndpoint(
-                path=path,
-                method=HttpMethod.POST,
-                request_model=Rodin3DDownloadRequest,
-                response_model=Rodin3DDownloadResponse,
-            ),
-            request=Rodin3DDownloadRequest(
-                task_uuid=uuid
-            ),
-            auth_kwargs=kwargs
-        )
-
-        return await operation.execute()
-
-    def get_quality_mode(self, poly_count):
-        if poly_count == "200K-Triangle":
-            mesh_mode = "Raw"
-            quality = "medium"
-        else:
-            mesh_mode = "Quad"
-            if poly_count == "4K-Quad":
-                quality = "extra-low"
-            elif poly_count == "8K-Quad":
-                quality = "low"
-            elif poly_count == "18K-Quad":
-                quality = "medium"
-            elif poly_count == "50K-Quad":
-                quality = "high"
-            else:
-                quality = "medium"
-
-        return mesh_mode, quality
-
-    async def download_files(self, url_list):
-        save_path = os.path.join(comfy_paths.get_output_directory(), "Rodin3D", datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S"))
-        os.makedirs(save_path, exist_ok=True)
-        model_file_path = None
-        async with aiohttp.ClientSession() as session:
-            for i in url_list.list:
-                url = i.url
-                file_name = i.name
-                file_path = os.path.join(save_path, file_name)
-                if file_path.endswith(".glb"):
-                    model_file_path = file_path
-                logging.info(f"[ Rodin3D API - download_files ] Downloading file: {file_path}")
-                max_retries = 5
-                for attempt in range(max_retries):
-                    try:
-                        async with session.get(url) as resp:
-                            resp.raise_for_status()
-                            with open(file_path, "wb") as f:
-                                async for chunk in resp.content.iter_chunked(32 * 1024):
-                                    f.write(chunk)
-                        break
-                    except Exception as e:
-                        logging.info(f"[ Rodin3D API - download_files ] Error downloading {file_path}:{e}")
-                        if attempt < max_retries - 1:
-                            logging.info("Retrying...")
-                            await asyncio.sleep(2)
-                        else:
-                            logging.info(
-                                "[ Rodin3D API - download_files ] Failed to download %s after %s attempts.",
-                                file_path,
-                                max_retries,
-                            )
-
-        return model_file_path
+def check_rodin_status(response: Rodin3DCheckStatusResponse) -> str:
+    all_done = all(job.status == JobStatus.Done for job in response.jobs)
+    status_list = [str(job.status) for job in response.jobs]
+    logging.info(f"[ Rodin3D API - CheckStatus ] Generate Status: {status_list}")
+    if any(job.status == JobStatus.Failed for job in response.jobs):
+        logging.error(f"[ Rodin3D API - CheckStatus ] Generate Failed: {status_list}, Please try again.")
+        raise Exception("[ Rodin3D API ] Generate Failed, Please Try again.")
+    if all_done:
+        return "DONE"
+    return "Generating"
 
 
-class Rodin3D_Regular(Rodin3DAPI):
+async def poll_for_task_status(
+    subscription_key, auth_kwargs: Optional[dict[str, str]] = None,
+) -> Rodin3DCheckStatusResponse:
+    poll_operation = PollingOperation(
+        poll_endpoint=ApiEndpoint(
+            path="/proxy/rodin/api/v2/status",
+            method=HttpMethod.POST,
+            request_model=Rodin3DCheckStatusRequest,
+            response_model=Rodin3DCheckStatusResponse,
+        ),
+        request=Rodin3DCheckStatusRequest(subscription_key=subscription_key),
+        completed_statuses=["DONE"],
+        failed_statuses=["FAILED"],
+        status_extractor=check_rodin_status,
+        poll_interval=3.0,
+        auth_kwargs=auth_kwargs,
+    )
+    logging.info("[ Rodin3D API - CheckStatus ] Generate Start!")
+    return await poll_operation.execute()
+
+
+async def get_rodin_download_list(uuid, auth_kwargs: Optional[dict[str, str]] = None) -> Rodin3DDownloadResponse:
+    logging.info("[ Rodin3D API - Downloading ] Generate Successfully!")
+    operation = SynchronousOperation(
+        endpoint=ApiEndpoint(
+            path="/proxy/rodin/api/v2/download",
+            method=HttpMethod.POST,
+            request_model=Rodin3DDownloadRequest,
+            response_model=Rodin3DDownloadResponse,
+        ),
+        request=Rodin3DDownloadRequest(task_uuid=uuid),
+        auth_kwargs=auth_kwargs,
+    )
+    return await operation.execute()
+
+
+async def download_files(url_list, task_uuid):
+    save_path = os.path.join(comfy_paths.get_output_directory(), f"Rodin3D_{task_uuid}")
+    os.makedirs(save_path, exist_ok=True)
+    model_file_path = None
+    async with aiohttp.ClientSession() as session:
+        for i in url_list.list:
+            url = i.url
+            file_name = i.name
+            file_path = os.path.join(save_path, file_name)
+            if file_path.endswith(".glb"):
+                model_file_path = file_path
+            logging.info(f"[ Rodin3D API - download_files ] Downloading file: {file_path}")
+            max_retries = 5
+            for attempt in range(max_retries):
+                try:
+                    async with session.get(url) as resp:
+                        resp.raise_for_status()
+                        with open(file_path, "wb") as f:
+                            async for chunk in resp.content.iter_chunked(32 * 1024):
+                                f.write(chunk)
+                    break
+                except Exception as e:
+                    logging.info(f"[ Rodin3D API - download_files ] Error downloading {file_path}:{e}")
+                    if attempt < max_retries - 1:
+                        logging.info("Retrying...")
+                        await asyncio.sleep(2)
+                    else:
+                        logging.info(
+                            "[ Rodin3D API - download_files ] Failed to download %s after %s attempts.",
+                            file_path,
+                            max_retries,
+                        )
+    return model_file_path
+
+
+class Rodin3D_Regular(comfy_io.ComfyNode):
+    """Generate 3D Assets using Rodin API"""
+
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "Images":
-                (
-                    IO.IMAGE,
-                    {
-                        "forceInput":True,
-                    }
-                )
-            },
-            "optional": {
-                **COMMON_PARAMETERS
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-            },
-        }
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="Rodin3D_Regular",
+            display_name="Rodin 3D Generate - Regular Generate",
+            category="api node/3d/Rodin",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("Images"),
+                *COMMON_PARAMETERS,
+            ],
+            outputs=[comfy_io.String.Output(display_name="3D Model Path")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+            ],
+            is_api_node=True,
+        )
 
-    async def api_call(
-        self,
+    @classmethod
+    async def execute(
+        cls,
         Images,
         Seed,
         Material_Type,
         Polygon_count,
-        **kwargs
-    ):
+    ) -> comfy_io.NodeOutput:
         tier = "Regular"
         num_images = Images.shape[0]
         m_images = []
         for i in range(num_images):
             m_images.append(Images[i])
-        mesh_mode, quality = self.get_quality_mode(Polygon_count)
-        task_uuid, subscription_key = await self.create_generate_task(images=m_images, seed=Seed, material=Material_Type,
-                                                                quality=quality, tier=tier, mesh_mode=mesh_mode,
-                                                                **kwargs)
-        await self.poll_for_task_status(subscription_key, **kwargs)
-        download_list = await self.get_rodin_download_list(task_uuid, **kwargs)
-        model = await self.download_files(download_list)
-
-        return (model,)
-
-
-class Rodin3D_Detail(Rodin3DAPI):
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "Images":
-                (
-                    IO.IMAGE,
-                    {
-                        "forceInput":True,
-                    }
-                )
-            },
-            "optional": {
-                **COMMON_PARAMETERS
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-            },
+        mesh_mode, quality_override = get_quality_mode(Polygon_count)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
         }
+        task_uuid, subscription_key = await create_generate_task(
+            images=m_images,
+            seed=Seed,
+            material=Material_Type,
+            quality_override=quality_override,
+            tier=tier,
+            mesh_mode=mesh_mode,
+            auth_kwargs=auth,
+        )
+        await poll_for_task_status(subscription_key, auth_kwargs=auth)
+        download_list = await get_rodin_download_list(task_uuid, auth_kwargs=auth)
+        model = await download_files(download_list, task_uuid)
 
-    async def api_call(
-        self,
+        return comfy_io.NodeOutput(model)
+
+
+class Rodin3D_Detail(comfy_io.ComfyNode):
+    """Generate 3D Assets using Rodin API"""
+
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="Rodin3D_Detail",
+            display_name="Rodin 3D Generate - Detail Generate",
+            category="api node/3d/Rodin",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("Images"),
+                *COMMON_PARAMETERS,
+            ],
+            outputs=[comfy_io.String.Output(display_name="3D Model Path")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
         Images,
         Seed,
         Material_Type,
         Polygon_count,
-        **kwargs
-    ):
+    ) -> comfy_io.NodeOutput:
         tier = "Detail"
         num_images = Images.shape[0]
         m_images = []
         for i in range(num_images):
             m_images.append(Images[i])
-        mesh_mode, quality = self.get_quality_mode(Polygon_count)
-        task_uuid, subscription_key = await self.create_generate_task(images=m_images, seed=Seed, material=Material_Type,
-                                                                quality=quality, tier=tier, mesh_mode=mesh_mode,
-                                                                **kwargs)
-        await self.poll_for_task_status(subscription_key, **kwargs)
-        download_list = await self.get_rodin_download_list(task_uuid, **kwargs)
-        model = await self.download_files(download_list)
-
-        return (model,)
-
-
-class Rodin3D_Smooth(Rodin3DAPI):
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "Images":
-                (
-                    IO.IMAGE,
-                    {
-                        "forceInput":True,
-                    }
-                )
-            },
-            "optional": {
-                **COMMON_PARAMETERS
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-            },
+        mesh_mode, quality_override = get_quality_mode(Polygon_count)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
         }
+        task_uuid, subscription_key = await create_generate_task(
+            images=m_images,
+            seed=Seed,
+            material=Material_Type,
+            quality_override=quality_override,
+            tier=tier,
+            mesh_mode=mesh_mode,
+            auth_kwargs=auth,
+        )
+        await poll_for_task_status(subscription_key, auth_kwargs=auth)
+        download_list = await get_rodin_download_list(task_uuid, auth_kwargs=auth)
+        model = await download_files(download_list, task_uuid)
 
-    async def api_call(
-        self,
+        return comfy_io.NodeOutput(model)
+
+
+class Rodin3D_Smooth(comfy_io.ComfyNode):
+    """Generate 3D Assets using Rodin API"""
+
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="Rodin3D_Smooth",
+            display_name="Rodin 3D Generate - Smooth Generate",
+            category="api node/3d/Rodin",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("Images"),
+                *COMMON_PARAMETERS,
+            ],
+            outputs=[comfy_io.String.Output(display_name="3D Model Path")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
         Images,
         Seed,
         Material_Type,
         Polygon_count,
-        **kwargs
-    ):
+    ) -> comfy_io.NodeOutput:
         tier = "Smooth"
         num_images = Images.shape[0]
         m_images = []
         for i in range(num_images):
             m_images.append(Images[i])
-        mesh_mode, quality = self.get_quality_mode(Polygon_count)
-        task_uuid, subscription_key = await self.create_generate_task(images=m_images, seed=Seed, material=Material_Type,
-                                                                quality=quality, tier=tier, mesh_mode=mesh_mode,
-                                                                **kwargs)
-        await self.poll_for_task_status(subscription_key, **kwargs)
-        download_list = await self.get_rodin_download_list(task_uuid, **kwargs)
-        model = await self.download_files(download_list)
-
-        return (model,)
-
-
-class Rodin3D_Sketch(Rodin3DAPI):
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "Images":
-                (
-                    IO.IMAGE,
-                    {
-                        "forceInput":True,
-                    }
-                )
-            },
-            "optional": {
-                "Seed":
-                (
-                    IO.INT,
-                    {
-                        "default":0,
-                        "min":0,
-                        "max":65535,
-                        "display":"number"
-                    }
-                )
-            },
-            "hidden": {
-                "auth_token": "AUTH_TOKEN_COMFY_ORG",
-                "comfy_api_key": "API_KEY_COMFY_ORG",
-            },
+        mesh_mode, quality_override = get_quality_mode(Polygon_count)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
         }
+        task_uuid, subscription_key = await create_generate_task(
+            images=m_images,
+            seed=Seed,
+            material=Material_Type,
+            quality_override=quality_override,
+            tier=tier,
+            mesh_mode=mesh_mode,
+            auth_kwargs=auth,
+        )
+        await poll_for_task_status(subscription_key, auth_kwargs=auth)
+        download_list = await get_rodin_download_list(task_uuid, auth_kwargs=auth)
+        model = await download_files(download_list, task_uuid)
 
-    async def api_call(
-        self,
+        return comfy_io.NodeOutput(model)
+
+
+class Rodin3D_Sketch(comfy_io.ComfyNode):
+    """Generate 3D Assets using Rodin API"""
+
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="Rodin3D_Sketch",
+            display_name="Rodin 3D Generate - Sketch Generate",
+            category="api node/3d/Rodin",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("Images"),
+                comfy_io.Int.Input(
+                    "Seed",
+                    default=0,
+                    min=0,
+                    max=65535,
+                    display_mode=comfy_io.NumberDisplay.number,
+                    optional=True,
+                ),
+            ],
+            outputs=[comfy_io.String.Output(display_name="3D Model Path")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
         Images,
         Seed,
-        **kwargs
-    ):
+    ) -> comfy_io.NodeOutput:
         tier = "Sketch"
         num_images = Images.shape[0]
         m_images = []
         for i in range(num_images):
             m_images.append(Images[i])
         material_type = "PBR"
-        quality = "medium"
+        quality_override = 18000
         mesh_mode = "Quad"
-        task_uuid, subscription_key = await self.create_generate_task(
-            images=m_images, seed=Seed, material=material_type, quality=quality, tier=tier, mesh_mode=mesh_mode, **kwargs
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
+        task_uuid, subscription_key = await create_generate_task(
+            images=m_images,
+            seed=Seed,
+            material=material_type,
+            quality_override=quality_override,
+            tier=tier,
+            mesh_mode=mesh_mode,
+            auth_kwargs=auth,
         )
-        await self.poll_for_task_status(subscription_key, **kwargs)
-        download_list = await self.get_rodin_download_list(task_uuid, **kwargs)
-        model = await self.download_files(download_list)
+        await poll_for_task_status(subscription_key, auth_kwargs=auth)
+        download_list = await get_rodin_download_list(task_uuid, auth_kwargs=auth)
+        model = await download_files(download_list, task_uuid)
 
-        return (model,)
+        return comfy_io.NodeOutput(model)
 
-# A dictionary that contains all nodes you want to export with their names
-# NOTE: names should be globally unique
-NODE_CLASS_MAPPINGS = {
-    "Rodin3D_Regular": Rodin3D_Regular,
-    "Rodin3D_Detail": Rodin3D_Detail,
-    "Rodin3D_Smooth": Rodin3D_Smooth,
-    "Rodin3D_Sketch": Rodin3D_Sketch,
-}
 
-# A dictionary that contains the friendly/humanly readable titles for the nodes
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "Rodin3D_Regular": "Rodin 3D Generate - Regular Generate",
-    "Rodin3D_Detail": "Rodin 3D Generate - Detail Generate",
-    "Rodin3D_Smooth": "Rodin 3D Generate - Smooth Generate",
-    "Rodin3D_Sketch": "Rodin 3D Generate - Sketch Generate",
-}
+class Rodin3D_Gen2(comfy_io.ComfyNode):
+    """Generate 3D Assets using Rodin API"""
+
+    @classmethod
+    def define_schema(cls) -> comfy_io.Schema:
+        return comfy_io.Schema(
+            node_id="Rodin3D_Gen2",
+            display_name="Rodin 3D Generate - Gen-2 Generate",
+            category="api node/3d/Rodin",
+            description=cleandoc(cls.__doc__ or ""),
+            inputs=[
+                comfy_io.Image.Input("Images"),
+                comfy_io.Int.Input(
+                    "Seed",
+                    default=0,
+                    min=0,
+                    max=65535,
+                    display_mode=comfy_io.NumberDisplay.number,
+                    optional=True,
+                ),
+                comfy_io.Combo.Input("Material_Type", options=["PBR", "Shaded"], default="PBR", optional=True),
+                comfy_io.Combo.Input(
+                    "Polygon_count",
+                    options=["4K-Quad", "8K-Quad", "18K-Quad", "50K-Quad", "2K-Triangle", "20K-Triangle", "150K-Triangle", "500K-Triangle"],
+                    default="500K-Triangle",
+                    optional=True,
+                ),
+                comfy_io.Boolean.Input("TAPose", default=False),
+            ],
+            outputs=[comfy_io.String.Output(display_name="3D Model Path")],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        Images,
+        Seed,
+        Material_Type,
+        Polygon_count,
+        TAPose,
+    ) -> comfy_io.NodeOutput:
+        tier = "Gen-2"
+        num_images = Images.shape[0]
+        m_images = []
+        for i in range(num_images):
+            m_images.append(Images[i])
+        mesh_mode, quality_override = get_quality_mode(Polygon_count)
+        auth = {
+            "auth_token": cls.hidden.auth_token_comfy_org,
+            "comfy_api_key": cls.hidden.api_key_comfy_org,
+        }
+        task_uuid, subscription_key = await create_generate_task(
+            images=m_images,
+            seed=Seed,
+            material=Material_Type,
+            quality_override=quality_override,
+            tier=tier,
+            mesh_mode=mesh_mode,
+            TAPose=TAPose,
+            auth_kwargs=auth,
+        )
+        await poll_for_task_status(subscription_key, auth_kwargs=auth)
+        download_list = await get_rodin_download_list(task_uuid, auth_kwargs=auth)
+        model = await download_files(download_list, task_uuid)
+
+        return comfy_io.NodeOutput(model)
+
+
+class Rodin3DExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
+        return [
+            Rodin3D_Regular,
+            Rodin3D_Detail,
+            Rodin3D_Smooth,
+            Rodin3D_Sketch,
+            Rodin3D_Gen2,
+        ]
+
+
+async def comfy_entrypoint() -> Rodin3DExtension:
+    return Rodin3DExtension()

comfy_api_nodes/nodes_wan.py

@@ -28,6 +28,12 @@ class Text2ImageInputField(BaseModel):
     negative_prompt: Optional[str] = Field(None)
 
 
+class Image2ImageInputField(BaseModel):
+    prompt: str = Field(...)
+    negative_prompt: Optional[str] = Field(None)
+    images: list[str] = Field(..., min_length=1, max_length=2)
+
+
 class Text2VideoInputField(BaseModel):
     prompt: str = Field(...)
     negative_prompt: Optional[str] = Field(None)
@@ -49,6 +55,13 @@ class Txt2ImageParametersField(BaseModel):
     watermark: bool = Field(True)
 
 
+class Image2ImageParametersField(BaseModel):
+    size: Optional[str] = Field(None)
+    n: int = Field(1, description="Number of images to generate.")  # we support only value=1
+    seed: int = Field(..., ge=0, le=2147483647)
+    watermark: bool = Field(True)
+
+
 class Text2VideoParametersField(BaseModel):
     size: str = Field(...)
     seed: int = Field(..., ge=0, le=2147483647)
@@ -73,6 +86,12 @@ class Text2ImageTaskCreationRequest(BaseModel):
     parameters: Txt2ImageParametersField = Field(...)
 
 
+class Image2ImageTaskCreationRequest(BaseModel):
+    model: str = Field(...)
+    input: Image2ImageInputField = Field(...)
+    parameters: Image2ImageParametersField = Field(...)
+
+
 class Text2VideoTaskCreationRequest(BaseModel):
     model: str = Field(...)
     input: Text2VideoInputField = Field(...)
@@ -135,7 +154,12 @@ async def process_task(
     url: str,
     request_model: Type[T],
     response_model: Type[R],
-    payload: Union[Text2ImageTaskCreationRequest, Text2VideoTaskCreationRequest, Image2VideoTaskCreationRequest],
+    payload: Union[
+        Text2ImageTaskCreationRequest,
+        Image2ImageTaskCreationRequest,
+        Text2VideoTaskCreationRequest,
+        Image2VideoTaskCreationRequest,
+    ],
     node_id: str,
     estimated_duration: int,
     poll_interval: int,
@@ -288,6 +312,128 @@ class WanTextToImageApi(comfy_io.ComfyNode):
         return comfy_io.NodeOutput(await download_url_to_image_tensor(str(response.output.results[0].url)))
 
 
+class WanImageToImageApi(comfy_io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return comfy_io.Schema(
+            node_id="WanImageToImageApi",
+            display_name="Wan Image to Image",
+            category="api node/image/Wan",
+            description="Generates an image from one or two input images and a text prompt. "
+                        "The output image is currently fixed at 1.6 MP; its aspect ratio matches the input image(s).",
+            inputs=[
+                comfy_io.Combo.Input(
+                    "model",
+                    options=["wan2.5-i2i-preview"],
+                    default="wan2.5-i2i-preview",
+                    tooltip="Model to use.",
+                ),
+                comfy_io.Image.Input(
+                    "image",
+                    tooltip="Single-image editing or multi-image fusion, maximum 2 images.",
+                ),
+                comfy_io.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Prompt used to describe the elements and visual features, supports English/Chinese.",
+                ),
+                comfy_io.String.Input(
+                    "negative_prompt",
+                    multiline=True,
+                    default="",
+                    tooltip="Negative text prompt to guide what to avoid.",
+                    optional=True,
+                ),
+                # redo this later as an optional combo of recommended resolutions
+                # comfy_io.Int.Input(
+                #     "width",
+                #     default=1280,
+                #     min=384,
+                #     max=1440,
+                #     step=16,
+                #     optional=True,
+                # ),
+                # comfy_io.Int.Input(
+                #     "height",
+                #     default=1280,
+                #     min=384,
+                #     max=1440,
+                #     step=16,
+                #     optional=True,
+                # ),
+                comfy_io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    step=1,
+                    display_mode=comfy_io.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed to use for generation.",
+                    optional=True,
+                ),
+                comfy_io.Boolean.Input(
+                    "watermark",
+                    default=True,
+                    tooltip="Whether to add an \"AI generated\" watermark to the result.",
+                    optional=True,
+                ),
+            ],
+            outputs=[
+                comfy_io.Image.Output(),
+            ],
+            hidden=[
+                comfy_io.Hidden.auth_token_comfy_org,
+                comfy_io.Hidden.api_key_comfy_org,
+                comfy_io.Hidden.unique_id,
+            ],
+            is_api_node=True,
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        model: str,
+        image: torch.Tensor,
+        prompt: str,
+        negative_prompt: str = "",
+        # width: int = 1024,
+        # height: int = 1024,
+        seed: int = 0,
+        watermark: bool = True,
+    ):
+        n_images = get_number_of_images(image)
+        if n_images not in (1, 2):
+            raise ValueError(f"Expected 1 or 2 input images, got {n_images}.")
+        images = []
+        for i in image:
+            images.append("data:image/png;base64," + tensor_to_base64_string(i, total_pixels=4096*4096))
+        payload = Image2ImageTaskCreationRequest(
+            model=model,
+            input=Image2ImageInputField(prompt=prompt, negative_prompt=negative_prompt, images=images),
+            parameters=Image2ImageParametersField(
+                # size=f"{width}*{height}",
+                seed=seed,
+                watermark=watermark,
+            ),
+        )
+        response = await process_task(
+            {
+                "auth_token": cls.hidden.auth_token_comfy_org,
+                "comfy_api_key": cls.hidden.api_key_comfy_org,
+            },
+            "/proxy/wan/api/v1/services/aigc/image2image/image-synthesis",
+            request_model=Image2ImageTaskCreationRequest,
+            response_model=ImageTaskStatusResponse,
+            payload=payload,
+            node_id=cls.hidden.unique_id,
+            estimated_duration=42,
+            poll_interval=3,
+        )
+        return comfy_io.NodeOutput(await download_url_to_image_tensor(str(response.output.results[0].url)))
+
+
 class WanTextToVideoApi(comfy_io.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -593,6 +739,7 @@ class WanApiExtension(ComfyExtension):
     async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
         return [
             WanTextToImageApi,
+            WanImageToImageApi,
             WanTextToVideoApi,
             WanImageToVideoApi,
         ]

comfy_extras/nodes_audio.py

@@ -11,6 +11,7 @@ import json
 import random
 import hashlib
 import node_helpers
+import logging
 from comfy.cli_args import args
 from comfy.comfy_types import FileLocator
 
@@ -359,11 +360,221 @@ class RecordAudio:
     def load(self, audio):
         audio_path = folder_paths.get_annotated_filepath(audio)
 
-        waveform, sample_rate = torchaudio.load(audio_path)
+        waveform, sample_rate = load(audio_path)
         audio = {"waveform": waveform.unsqueeze(0), "sample_rate": sample_rate}
         return (audio, )
 
 
+class TrimAudioDuration:
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "audio": ("AUDIO",),
+                "start_index": ("FLOAT", {"default": 0.0, "min": -0xffffffffffffffff, "max": 0xffffffffffffffff, "step": 0.01, "tooltip": "Start time in seconds, can be negative to count from the end (supports sub-seconds)."}),
+                "duration": ("FLOAT", {"default": 60.0, "min": 0.0, "step": 0.01, "tooltip": "Duration in seconds"}),
+            },
+        }
+
+    FUNCTION = "trim"
+    RETURN_TYPES = ("AUDIO",)
+    CATEGORY = "audio"
+    DESCRIPTION = "Trim audio tensor into chosen time range."
+
+    def trim(self, audio, start_index, duration):
+        waveform = audio["waveform"]
+        sample_rate = audio["sample_rate"]
+        audio_length = waveform.shape[-1]
+
+        if start_index < 0:
+            start_frame = audio_length + int(round(start_index * sample_rate))
+        else:
+            start_frame = int(round(start_index * sample_rate))
+        start_frame = max(0, min(start_frame, audio_length - 1))
+
+        end_frame = start_frame + int(round(duration * sample_rate))
+        end_frame = max(0, min(end_frame, audio_length))
+
+        if start_frame >= end_frame:
+            raise ValueError("AudioTrim: Start time must be less than end time and be within the audio length.")
+
+        return ({"waveform": waveform[..., start_frame:end_frame], "sample_rate": sample_rate},)
+
+
+class SplitAudioChannels:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "audio": ("AUDIO",),
+        }}
+
+    RETURN_TYPES = ("AUDIO", "AUDIO")
+    RETURN_NAMES = ("left", "right")
+    FUNCTION = "separate"
+    CATEGORY = "audio"
+    DESCRIPTION = "Separates the audio into left and right channels."
+
+    def separate(self, audio):
+        waveform = audio["waveform"]
+        sample_rate = audio["sample_rate"]
+
+        if waveform.shape[1] != 2:
+            raise ValueError("AudioSplit: Input audio has only one channel.")
+
+        left_channel = waveform[..., 0:1, :]
+        right_channel = waveform[..., 1:2, :]
+
+        return ({"waveform": left_channel, "sample_rate": sample_rate}, {"waveform": right_channel, "sample_rate": sample_rate})
+
+
+def match_audio_sample_rates(waveform_1, sample_rate_1, waveform_2, sample_rate_2):
+    if sample_rate_1 != sample_rate_2:
+        if sample_rate_1 > sample_rate_2:
+            waveform_2 = torchaudio.functional.resample(waveform_2, sample_rate_2, sample_rate_1)
+            output_sample_rate = sample_rate_1
+            logging.info(f"Resampling audio2 from {sample_rate_2}Hz to {sample_rate_1}Hz for merging.")
+        else:
+            waveform_1 = torchaudio.functional.resample(waveform_1, sample_rate_1, sample_rate_2)
+            output_sample_rate = sample_rate_2
+            logging.info(f"Resampling audio1 from {sample_rate_1}Hz to {sample_rate_2}Hz for merging.")
+    else:
+        output_sample_rate = sample_rate_1
+    return waveform_1, waveform_2, output_sample_rate
+
+
+class AudioConcat:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "audio1": ("AUDIO",),
+            "audio2": ("AUDIO",),
+            "direction": (['after', 'before'], {"default": 'after', "tooltip": "Whether to append audio2 after or before audio1."}),
+        }}
+
+    RETURN_TYPES = ("AUDIO",)
+    FUNCTION = "concat"
+    CATEGORY = "audio"
+    DESCRIPTION = "Concatenates the audio1 to audio2 in the specified direction."
+
+    def concat(self, audio1, audio2, direction):
+        waveform_1 = audio1["waveform"]
+        waveform_2 = audio2["waveform"]
+        sample_rate_1 = audio1["sample_rate"]
+        sample_rate_2 = audio2["sample_rate"]
+
+        if waveform_1.shape[1] == 1:
+            waveform_1 = waveform_1.repeat(1, 2, 1)
+            logging.info("AudioConcat: Converted mono audio1 to stereo by duplicating the channel.")
+        if waveform_2.shape[1] == 1:
+            waveform_2 = waveform_2.repeat(1, 2, 1)
+            logging.info("AudioConcat: Converted mono audio2 to stereo by duplicating the channel.")
+
+        waveform_1, waveform_2, output_sample_rate = match_audio_sample_rates(waveform_1, sample_rate_1, waveform_2, sample_rate_2)
+
+        if direction == 'after':
+            concatenated_audio = torch.cat((waveform_1, waveform_2), dim=2)
+        elif direction == 'before':
+            concatenated_audio = torch.cat((waveform_2, waveform_1), dim=2)
+
+        return ({"waveform": concatenated_audio, "sample_rate": output_sample_rate},)
+
+
+class AudioMerge:
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "audio1": ("AUDIO",),
+                "audio2": ("AUDIO",),
+                "merge_method": (["add", "mean", "subtract", "multiply"], {"tooltip": "The method used to combine the audio waveforms."}),
+            },
+        }
+
+    FUNCTION = "merge"
+    RETURN_TYPES = ("AUDIO",)
+    CATEGORY = "audio"
+    DESCRIPTION = "Combine two audio tracks by overlaying their waveforms."
+
+    def merge(self, audio1, audio2, merge_method):
+        waveform_1 = audio1["waveform"]
+        waveform_2 = audio2["waveform"]
+        sample_rate_1 = audio1["sample_rate"]
+        sample_rate_2 = audio2["sample_rate"]
+
+        waveform_1, waveform_2, output_sample_rate = match_audio_sample_rates(waveform_1, sample_rate_1, waveform_2, sample_rate_2)
+
+        length_1 = waveform_1.shape[-1]
+        length_2 = waveform_2.shape[-1]
+
+        if length_2 > length_1:
+            logging.info(f"AudioMerge: Trimming audio2 from {length_2} to {length_1} samples to match audio1 length.")
+            waveform_2 = waveform_2[..., :length_1]
+        elif length_2 < length_1:
+            logging.info(f"AudioMerge: Padding audio2 from {length_2} to {length_1} samples to match audio1 length.")
+            pad_shape = list(waveform_2.shape)
+            pad_shape[-1] = length_1 - length_2
+            pad_tensor = torch.zeros(pad_shape, dtype=waveform_2.dtype, device=waveform_2.device)
+            waveform_2 = torch.cat((waveform_2, pad_tensor), dim=-1)
+
+        if merge_method == "add":
+            waveform = waveform_1 + waveform_2
+        elif merge_method == "subtract":
+            waveform = waveform_1 - waveform_2
+        elif merge_method == "multiply":
+            waveform = waveform_1 * waveform_2
+        elif merge_method == "mean":
+            waveform = (waveform_1 + waveform_2) / 2
+
+        max_val = waveform.abs().max()
+        if max_val > 1.0:
+            waveform = waveform / max_val
+
+        return ({"waveform": waveform, "sample_rate": output_sample_rate},)
+
+
+class AudioAdjustVolume:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "audio": ("AUDIO",),
+            "volume": ("INT", {"default": 1.0, "min": -100, "max": 100, "tooltip": "Volume adjustment in decibels (dB). 0 = no change, +6 = double, -6 = half, etc"}),
+        }}
+
+    RETURN_TYPES = ("AUDIO",)
+    FUNCTION = "adjust_volume"
+    CATEGORY = "audio"
+
+    def adjust_volume(self, audio, volume):
+        if volume == 0:
+            return (audio,)
+        waveform = audio["waveform"]
+        sample_rate = audio["sample_rate"]
+
+        gain = 10 ** (volume / 20)
+        waveform = waveform * gain
+
+        return ({"waveform": waveform, "sample_rate": sample_rate},)
+
+
+class EmptyAudio:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "duration": ("FLOAT", {"default": 60.0, "min": 0.0, "max": 0xffffffffffffffff, "step": 0.01, "tooltip": "Duration of the empty audio clip in seconds"}),
+            "sample_rate": ("INT", {"default": 44100, "tooltip": "Sample rate of the empty audio clip."}),
+            "channels": ("INT", {"default": 2, "min": 1, "max": 2, "tooltip": "Number of audio channels (1 for mono, 2 for stereo)."}),
+        }}
+
+    RETURN_TYPES = ("AUDIO",)
+    FUNCTION = "create_empty_audio"
+    CATEGORY = "audio"
+
+    def create_empty_audio(self, duration, sample_rate, channels):
+        num_samples = int(round(duration * sample_rate))
+        waveform = torch.zeros((1, channels, num_samples), dtype=torch.float32)
+        return ({"waveform": waveform, "sample_rate": sample_rate},)
+
+
 NODE_CLASS_MAPPINGS = {
     "EmptyLatentAudio": EmptyLatentAudio,
     "VAEEncodeAudio": VAEEncodeAudio,
@@ -375,6 +586,12 @@ NODE_CLASS_MAPPINGS = {
     "PreviewAudio": PreviewAudio,
     "ConditioningStableAudio": ConditioningStableAudio,
     "RecordAudio": RecordAudio,
+    "TrimAudioDuration": TrimAudioDuration,
+    "SplitAudioChannels": SplitAudioChannels,
+    "AudioConcat": AudioConcat,
+    "AudioMerge": AudioMerge,
+    "AudioAdjustVolume": AudioAdjustVolume,
+    "EmptyAudio": EmptyAudio,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -387,4 +604,10 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "SaveAudioMP3": "Save Audio (MP3)",
     "SaveAudioOpus": "Save Audio (Opus)",
     "RecordAudio": "Record Audio",
+    "TrimAudioDuration": "Trim Audio Duration",
+    "SplitAudioChannels": "Split Audio Channels",
+    "AudioConcat": "Audio Concat",
+    "AudioMerge": "Audio Merge",
+    "AudioAdjustVolume": "Audio Adjust Volume",
+    "EmptyAudio": "Empty Audio",
 }

comfy_extras/nodes_audio_encoder.py

@@ -1,44 +1,62 @@
 import folder_paths
 import comfy.audio_encoders.audio_encoders
 import comfy.utils
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 
-class AudioEncoderLoader:
+class AudioEncoderLoader(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "audio_encoder_name": (folder_paths.get_filename_list("audio_encoders"), ),
-                             }}
-    RETURN_TYPES = ("AUDIO_ENCODER",)
-    FUNCTION = "load_model"
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="AudioEncoderLoader",
+            category="loaders",
+            inputs=[
+                io.Combo.Input(
+                    "audio_encoder_name",
+                    options=folder_paths.get_filename_list("audio_encoders"),
+                ),
+            ],
+            outputs=[io.AudioEncoder.Output()],
+        )
 
-    CATEGORY = "loaders"
-
-    def load_model(self, audio_encoder_name):
+    @classmethod
+    def execute(cls, audio_encoder_name) -> io.NodeOutput:
         audio_encoder_name = folder_paths.get_full_path_or_raise("audio_encoders", audio_encoder_name)
         sd = comfy.utils.load_torch_file(audio_encoder_name, safe_load=True)
         audio_encoder = comfy.audio_encoders.audio_encoders.load_audio_encoder_from_sd(sd)
         if audio_encoder is None:
             raise RuntimeError("ERROR: audio encoder file is invalid and does not contain a valid model.")
-        return (audio_encoder,)
+        return io.NodeOutput(audio_encoder)
 
 
-class AudioEncoderEncode:
+class AudioEncoderEncode(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "audio_encoder": ("AUDIO_ENCODER",),
-                              "audio": ("AUDIO",),
-                             }}
-    RETURN_TYPES = ("AUDIO_ENCODER_OUTPUT",)
-    FUNCTION = "encode"
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="AudioEncoderEncode",
+            category="conditioning",
+            inputs=[
+                io.AudioEncoder.Input("audio_encoder"),
+                io.Audio.Input("audio"),
+            ],
+            outputs=[io.AudioEncoderOutput.Output()],
+        )
 
-    CATEGORY = "conditioning"
-
-    def encode(self, audio_encoder, audio):
+    @classmethod
+    def execute(cls, audio_encoder, audio) -> io.NodeOutput:
         output = audio_encoder.encode_audio(audio["waveform"], audio["sample_rate"])
-        return (output,)
+        return io.NodeOutput(output)
 
 
-NODE_CLASS_MAPPINGS = {
-    "AudioEncoderLoader": AudioEncoderLoader,
-    "AudioEncoderEncode": AudioEncoderEncode,
-}
+class AudioEncoder(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            AudioEncoderLoader,
+            AudioEncoderEncode,
+        ]
+
+
+async def comfy_entrypoint() -> AudioEncoder:
+    return AudioEncoder()

comfy_extras/nodes_clip_sdxl.py

@@ -1,43 +1,52 @@
-from nodes import MAX_RESOLUTION
+from typing_extensions import override
 
-class CLIPTextEncodeSDXLRefiner:
+import nodes
+from comfy_api.latest import ComfyExtension, io
+
+
+class CLIPTextEncodeSDXLRefiner(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "ascore": ("FLOAT", {"default": 6.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
-            "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
-            }}
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeSDXLRefiner",
+            category="advanced/conditioning",
+            inputs=[
+                io.Float.Input("ascore", default=6.0, min=0.0, max=1000.0, step=0.01),
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.String.Input("text", multiline=True, dynamic_prompts=True),
+                io.Clip.Input("clip"),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
 
-    CATEGORY = "advanced/conditioning"
-
-    def encode(self, clip, ascore, width, height, text):
+    @classmethod
+    def execute(cls, clip, ascore, width, height, text) -> io.NodeOutput:
         tokens = clip.tokenize(text)
-        return (clip.encode_from_tokens_scheduled(tokens, add_dict={"aesthetic_score": ascore, "width": width, "height": height}), )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"aesthetic_score": ascore, "width": width, "height": height}))
 
-class CLIPTextEncodeSDXL:
+class CLIPTextEncodeSDXL(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "clip": ("CLIP", ),
-            "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "crop_w": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
-            "crop_h": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
-            "target_width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "target_height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "text_g": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            "text_l": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            }}
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeSDXL",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("crop_w", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("crop_h", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("target_width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("target_height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.String.Input("text_g", multiline=True, dynamic_prompts=True),
+                io.String.Input("text_l", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
 
-    CATEGORY = "advanced/conditioning"
-
-    def encode(self, clip, width, height, crop_w, crop_h, target_width, target_height, text_g, text_l):
+    @classmethod
+    def execute(cls, clip, width, height, crop_w, crop_h, target_width, target_height, text_g, text_l) -> io.NodeOutput:
         tokens = clip.tokenize(text_g)
         tokens["l"] = clip.tokenize(text_l)["l"]
         if len(tokens["l"]) != len(tokens["g"]):
@@ -46,9 +55,17 @@ class CLIPTextEncodeSDXL:
                 tokens["l"] += empty["l"]
             while len(tokens["l"]) > len(tokens["g"]):
                 tokens["g"] += empty["g"]
-        return (clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height, "crop_w": crop_w, "crop_h": crop_h, "target_width": target_width, "target_height": target_height}), )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height, "crop_w": crop_w, "crop_h": crop_h, "target_width": target_width, "target_height": target_height}))
 
-NODE_CLASS_MAPPINGS = {
-    "CLIPTextEncodeSDXLRefiner": CLIPTextEncodeSDXLRefiner,
-    "CLIPTextEncodeSDXL": CLIPTextEncodeSDXL,
-}
+
+class ClipSdxlExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            CLIPTextEncodeSDXLRefiner,
+            CLIPTextEncodeSDXL,
+        ]
+
+
+async def comfy_entrypoint() -> ClipSdxlExtension:
+    return ClipSdxlExtension()

comfy_extras/nodes_differential_diffusion.py

@@ -1,34 +1,41 @@
 # code adapted from https://github.com/exx8/differential-diffusion
 
+from typing_extensions import override
+
 import torch
+from comfy_api.latest import ComfyExtension, io
 
-class DifferentialDiffusion():
+
+class DifferentialDiffusion(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "model": ("MODEL", ),
-            },
-            "optional": {
-                "strength": ("FLOAT", {
-                    "default": 1.0,
-                    "min": 0.0,
-                    "max": 1.0,
-                    "step": 0.01,
-                }),
-            }
-        }
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "apply"
-    CATEGORY = "_for_testing"
-    INIT = False
+    def define_schema(cls):
+        return io.Schema(
+            node_id="DifferentialDiffusion",
+            display_name="Differential Diffusion",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input(
+                    "strength",
+                    default=1.0,
+                    min=0.0,
+                    max=1.0,
+                    step=0.01,
+                    optional=True,
+                ),
+            ],
+            outputs=[io.Model.Output()],
+            is_experimental=True,
+        )
 
-    def apply(self, model, strength=1.0):
+    @classmethod
+    def execute(cls, model, strength=1.0) -> io.NodeOutput:
         model = model.clone()
-        model.set_model_denoise_mask_function(lambda *args, **kwargs: self.forward(*args, **kwargs, strength=strength))
-        return (model, )
+        model.set_model_denoise_mask_function(lambda *args, **kwargs: cls.forward(*args, **kwargs, strength=strength))
+        return io.NodeOutput(model)
 
-    def forward(self, sigma: torch.Tensor, denoise_mask: torch.Tensor, extra_options: dict, strength: float):
+    @classmethod
+    def forward(cls, sigma: torch.Tensor, denoise_mask: torch.Tensor, extra_options: dict, strength: float):
         model = extra_options["model"]
         step_sigmas = extra_options["sigmas"]
         sigma_to = model.inner_model.model_sampling.sigma_min
@@ -53,9 +60,13 @@ class DifferentialDiffusion():
             return binary_mask
 
 
-NODE_CLASS_MAPPINGS = {
-    "DifferentialDiffusion": DifferentialDiffusion,
-}
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "DifferentialDiffusion": "Differential Diffusion",
-}
+class DifferentialDiffusionExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            DifferentialDiffusion,
+        ]
+
+
+async def comfy_entrypoint() -> DifferentialDiffusionExtension:
+    return DifferentialDiffusionExtension()

comfy_extras/nodes_edit_model.py

@@ -1,26 +1,38 @@
 import node_helpers
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 
-class ReferenceLatent:
+class ReferenceLatent(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"conditioning": ("CONDITIONING", ),
-                            },
-                "optional": {"latent": ("LATENT", ),}
-               }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ReferenceLatent",
+            category="advanced/conditioning/edit_models",
+            description="This node sets the guiding latent for an edit model. If the model supports it you can chain multiple to set multiple reference images.",
+            inputs=[
+                io.Conditioning.Input("conditioning"),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ]
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "append"
-
-    CATEGORY = "advanced/conditioning/edit_models"
-    DESCRIPTION = "This node sets the guiding latent for an edit model. If the model supports it you can chain multiple to set multiple reference images."
-
-    def append(self, conditioning, latent=None):
+    @classmethod
+    def execute(cls, conditioning, latent=None) -> io.NodeOutput:
         if latent is not None:
             conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_latents": [latent["samples"]]}, append=True)
-        return (conditioning, )
+        return io.NodeOutput(conditioning)
 
 
-NODE_CLASS_MAPPINGS = {
-    "ReferenceLatent": ReferenceLatent,
-}
+class EditModelExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            ReferenceLatent,
+        ]
+
+
+def comfy_entrypoint() -> EditModelExtension:
+    return EditModelExtension()

comfy_extras/nodes_eps.py

@@ -0,0 +1,74 @@
+from typing_extensions import override
+
+from comfy_api.latest import ComfyExtension, io
+
+
+class EpsilonScaling(io.ComfyNode):
+    """
+    Implements the Epsilon Scaling method from 'Elucidating the Exposure Bias in Diffusion Models'
+    (https://arxiv.org/abs/2308.15321v6).
+
+    This method mitigates exposure bias by scaling the predicted noise during sampling,
+    which can significantly improve sample quality. This implementation uses the "uniform schedule"
+    recommended by the paper for its practicality and effectiveness.
+    """
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Epsilon Scaling",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input(
+                    "scaling_factor",
+                    default=1.005,
+                    min=0.5,
+                    max=1.5,
+                    step=0.001,
+                    display_mode=io.NumberDisplay.number,
+                ),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, scaling_factor) -> io.NodeOutput:
+        # Prevent division by zero, though the UI's min value should prevent this.
+        if scaling_factor == 0:
+            scaling_factor = 1e-9
+
+        def epsilon_scaling_function(args):
+            """
+            This function is applied after the CFG guidance has been calculated.
+            It recalculates the denoised latent by scaling the predicted noise.
+            """
+            denoised = args["denoised"]
+            x = args["input"]
+
+            noise_pred = x - denoised
+
+            scaled_noise_pred = noise_pred / scaling_factor
+
+            new_denoised = x - scaled_noise_pred
+
+            return new_denoised
+
+        # Clone the model patcher to avoid modifying the original model in place
+        model_clone = model.clone()
+
+        model_clone.set_model_sampler_post_cfg_function(epsilon_scaling_function)
+
+        return io.NodeOutput(model_clone)
+
+
+class EpsilonScalingExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            EpsilonScaling,
+        ]
+
+async def comfy_entrypoint() -> EpsilonScalingExtension:
+    return EpsilonScalingExtension()

comfy_extras/nodes_fresca.py

@@ -1,6 +1,8 @@
 # Code based on https://github.com/WikiChao/FreSca (MIT License)
 import torch
 import torch.fft as fft
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 
 def Fourier_filter(x, scale_low=1.0, scale_high=1.5, freq_cutoff=20):
@@ -51,25 +53,31 @@ def Fourier_filter(x, scale_low=1.0, scale_high=1.5, freq_cutoff=20):
     return x_filtered
 
 
-class FreSca:
+class FreSca(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "model": ("MODEL",),
-                "scale_low": ("FLOAT", {"default": 1.0, "min": 0, "max": 10, "step": 0.01,
-                                        "tooltip": "Scaling factor for low-frequency components"}),
-                "scale_high": ("FLOAT", {"default": 1.25, "min": 0, "max": 10, "step": 0.01,
-                                        "tooltip": "Scaling factor for high-frequency components"}),
-                "freq_cutoff": ("INT", {"default": 20, "min": 1, "max": 10000, "step": 1,
-                                        "tooltip": "Number of frequency indices around center to consider as low-frequency"}),
-            }
-        }
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
-    CATEGORY = "_for_testing"
-    DESCRIPTION = "Applies frequency-dependent scaling to the guidance"
-    def patch(self, model, scale_low, scale_high, freq_cutoff):
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FreSca",
+            display_name="FreSca",
+            category="_for_testing",
+            description="Applies frequency-dependent scaling to the guidance",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale_low", default=1.0, min=0, max=10, step=0.01,
+                               tooltip="Scaling factor for low-frequency components"),
+                io.Float.Input("scale_high", default=1.25, min=0, max=10, step=0.01,
+                               tooltip="Scaling factor for high-frequency components"),
+                io.Int.Input("freq_cutoff", default=20, min=1, max=10000, step=1,
+                             tooltip="Number of frequency indices around center to consider as low-frequency"),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, scale_low, scale_high, freq_cutoff):
         def custom_cfg_function(args):
             conds_out = args["conds_out"]
             if len(conds_out) <= 1 or None in args["conds"][:2]:
@@ -91,13 +99,16 @@ class FreSca:
         m = model.clone()
         m.set_model_sampler_pre_cfg_function(custom_cfg_function)
 
-        return (m,)
+        return io.NodeOutput(m)
 
 
-NODE_CLASS_MAPPINGS = {
-    "FreSca": FreSca,
-}
+class FreScaExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            FreSca,
+        ]
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "FreSca": "FreSca",
-}
+
+async def comfy_entrypoint() -> FreScaExtension:
+    return FreScaExtension()

comfy_extras/nodes_gits.py

@@ -1,6 +1,8 @@
 # from https://github.com/zju-pi/diff-sampler/tree/main/gits-main
 import numpy as np
 import torch
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 def loglinear_interp(t_steps, num_steps):
     """
@@ -333,25 +335,28 @@ NOISE_LEVELS = {
     ],
 }
 
-class GITSScheduler:
+class GITSScheduler(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"coeff": ("FLOAT", {"default": 1.20, "min": 0.80, "max": 1.50, "step": 0.05}),
-                     "steps": ("INT", {"default": 10, "min": 2, "max": 1000}),
-                     "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
-                      }
-               }
-    RETURN_TYPES = ("SIGMAS",)
-    CATEGORY = "sampling/custom_sampling/schedulers"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="GITSScheduler",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Float.Input("coeff", default=1.20, min=0.80, max=1.50, step=0.05),
+                io.Int.Input("steps", default=10, min=2, max=1000),
+                io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
 
-    FUNCTION = "get_sigmas"
-
-    def get_sigmas(self, coeff, steps, denoise):
+    @classmethod
+    def execute(cls, coeff, steps, denoise):
         total_steps = steps
         if denoise < 1.0:
             if denoise <= 0.0:
-                return (torch.FloatTensor([]),)
+                return io.NodeOutput(torch.FloatTensor([]))
             total_steps = round(steps * denoise)
 
         if steps <= 20:
@@ -362,8 +367,16 @@ class GITSScheduler:
 
         sigmas = sigmas[-(total_steps + 1):]
         sigmas[-1] = 0
-        return (torch.FloatTensor(sigmas), )
+        return io.NodeOutput(torch.FloatTensor(sigmas))
 
-NODE_CLASS_MAPPINGS = {
-    "GITSScheduler": GITSScheduler,
-}
+
+class GITSSchedulerExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            GITSScheduler,
+        ]
+
+
+async def comfy_entrypoint() -> GITSSchedulerExtension:
+    return GITSSchedulerExtension()

comfy_extras/nodes_hidream.py

@@ -1,55 +1,73 @@
+from typing_extensions import override
+
 import folder_paths
 import comfy.sd
 import comfy.model_management
+from comfy_api.latest import ComfyExtension, io
 
 
-class QuadrupleCLIPLoader:
+class QuadrupleCLIPLoader(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "clip_name1": (folder_paths.get_filename_list("text_encoders"), ),
-                              "clip_name2": (folder_paths.get_filename_list("text_encoders"), ),
-                              "clip_name3": (folder_paths.get_filename_list("text_encoders"), ),
-                              "clip_name4": (folder_paths.get_filename_list("text_encoders"), )
-                             }}
-    RETURN_TYPES = ("CLIP",)
-    FUNCTION = "load_clip"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="QuadrupleCLIPLoader",
+            category="advanced/loaders",
+            description="[Recipes]\n\nhidream: long clip-l, long clip-g, t5xxl, llama_8b_3.1_instruct",
+            inputs=[
+                io.Combo.Input("clip_name1", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name2", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name3", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name4", options=folder_paths.get_filename_list("text_encoders")),
+            ],
+            outputs=[
+                io.Clip.Output(),
+            ]
+        )
 
-    CATEGORY = "advanced/loaders"
-
-    DESCRIPTION = "[Recipes]\n\nhidream: long clip-l, long clip-g, t5xxl, llama_8b_3.1_instruct"
-
-    def load_clip(self, clip_name1, clip_name2, clip_name3, clip_name4):
+    @classmethod
+    def execute(cls, clip_name1, clip_name2, clip_name3, clip_name4):
         clip_path1 = folder_paths.get_full_path_or_raise("text_encoders", clip_name1)
         clip_path2 = folder_paths.get_full_path_or_raise("text_encoders", clip_name2)
         clip_path3 = folder_paths.get_full_path_or_raise("text_encoders", clip_name3)
         clip_path4 = folder_paths.get_full_path_or_raise("text_encoders", clip_name4)
         clip = comfy.sd.load_clip(ckpt_paths=[clip_path1, clip_path2, clip_path3, clip_path4], embedding_directory=folder_paths.get_folder_paths("embeddings"))
-        return (clip,)
+        return io.NodeOutput(clip)
 
-class CLIPTextEncodeHiDream:
+class CLIPTextEncodeHiDream(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "clip": ("CLIP", ),
-            "clip_l": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            "clip_g": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            "t5xxl": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            "llama": ("STRING", {"multiline": True, "dynamicPrompts": True})
-            }}
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
-
-    CATEGORY = "advanced/conditioning"
-
-    def encode(self, clip, clip_l, clip_g, t5xxl, llama):
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeHiDream",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("clip_l", multiline=True, dynamic_prompts=True),
+                io.String.Input("clip_g", multiline=True, dynamic_prompts=True),
+                io.String.Input("t5xxl", multiline=True, dynamic_prompts=True),
+                io.String.Input("llama", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ]
+        )
 
+    @classmethod
+    def execute(cls, clip, clip_l, clip_g, t5xxl, llama):
         tokens = clip.tokenize(clip_g)
         tokens["l"] = clip.tokenize(clip_l)["l"]
         tokens["t5xxl"] = clip.tokenize(t5xxl)["t5xxl"]
         tokens["llama"] = clip.tokenize(llama)["llama"]
-        return (clip.encode_from_tokens_scheduled(tokens), )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
 
-NODE_CLASS_MAPPINGS = {
-    "QuadrupleCLIPLoader": QuadrupleCLIPLoader,
-    "CLIPTextEncodeHiDream": CLIPTextEncodeHiDream,
-}
+
+class HiDreamExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            QuadrupleCLIPLoader,
+            CLIPTextEncodeHiDream,
+        ]
+
+
+async def comfy_entrypoint() -> HiDreamExtension:
+    return HiDreamExtension()

comfy_extras/nodes_hypertile.py

@@ -1,9 +1,11 @@
 #Taken from: https://github.com/tfernd/HyperTile/
 
 import math
+from typing_extensions import override
 from einops import rearrange
 # Use torch rng for consistency across generations
 from torch import randint
+from comfy_api.latest import ComfyExtension, io
 
 def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
     min_value = min(min_value, value)
@@ -20,25 +22,31 @@ def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
 
     return ns[idx]
 
-class HyperTile:
+class HyperTile(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                             "tile_size": ("INT", {"default": 256, "min": 1, "max": 2048}),
-                             "swap_size": ("INT", {"default": 2, "min": 1, "max": 128}),
-                             "max_depth": ("INT", {"default": 0, "min": 0, "max": 10}),
-                             "scale_depth": ("BOOLEAN", {"default": False}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="HyperTile",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Int.Input("tile_size", default=256, min=1, max=2048),
+                io.Int.Input("swap_size", default=2, min=1, max=128),
+                io.Int.Input("max_depth", default=0, min=0, max=10),
+                io.Boolean.Input("scale_depth", default=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    CATEGORY = "model_patches/unet"
-
-    def patch(self, model, tile_size, swap_size, max_depth, scale_depth):
+    @classmethod
+    def execute(cls, model, tile_size, swap_size, max_depth, scale_depth) -> io.NodeOutput:
         latent_tile_size = max(32, tile_size) // 8
-        self.temp = None
+        temp = None
 
         def hypertile_in(q, k, v, extra_options):
+            nonlocal temp
             model_chans = q.shape[-2]
             orig_shape = extra_options['original_shape']
             apply_to = []
@@ -58,14 +66,15 @@ class HyperTile:
 
                 if nh * nw > 1:
                     q = rearrange(q, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw)
-                    self.temp = (nh, nw, h, w)
+                    temp = (nh, nw, h, w)
                 return q, k, v
 
             return q, k, v
         def hypertile_out(out, extra_options):
-            if self.temp is not None:
-                nh, nw, h, w = self.temp
-                self.temp = None
+            nonlocal temp
+            if temp is not None:
+                nh, nw, h, w = temp
+                temp = None
                 out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw)
                 out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw)
             return out
@@ -76,6 +85,14 @@ class HyperTile:
         m.set_model_attn1_output_patch(hypertile_out)
         return (m, )
 
-NODE_CLASS_MAPPINGS = {
-    "HyperTile": HyperTile,
-}
+
+class HyperTileExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            HyperTile,
+        ]
+
+
+async def comfy_entrypoint() -> HyperTileExtension:
+    return HyperTileExtension()

comfy_extras/nodes_ip2p.py

@@ -1,21 +1,30 @@
 import torch
 
-class InstructPixToPixConditioning:
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
+
+
+class InstructPixToPixConditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"positive": ("CONDITIONING", ),
-                             "negative": ("CONDITIONING", ),
-                             "vae": ("VAE", ),
-                             "pixels": ("IMAGE", ),
-                             }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="InstructPixToPixConditioning",
+            category="conditioning/instructpix2pix",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Image.Input("pixels"),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING","CONDITIONING","LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
-    FUNCTION = "encode"
-
-    CATEGORY = "conditioning/instructpix2pix"
-
-    def encode(self, positive, negative, pixels, vae):
+    @classmethod
+    def execute(cls, positive, negative, pixels, vae) -> io.NodeOutput:
         x = (pixels.shape[1] // 8) * 8
         y = (pixels.shape[2] // 8) * 8
 
@@ -38,8 +47,17 @@ class InstructPixToPixConditioning:
                 n = [t[0], d]
                 c.append(n)
             out.append(c)
-        return (out[0], out[1], out_latent)
+        return io.NodeOutput(out[0], out[1], out_latent)
+
+
+class InstructPix2PixExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            InstructPixToPixConditioning,
+        ]
+
+
+async def comfy_entrypoint() -> InstructPix2PixExtension:
+    return InstructPix2PixExtension()
 
-NODE_CLASS_MAPPINGS = {
-    "InstructPixToPixConditioning": InstructPixToPixConditioning,
-}

comfy_extras/nodes_lotus.py

@@ -1,20 +1,22 @@
+from typing_extensions import override
+
 import torch
 import comfy.model_management as mm
+from comfy_api.latest import ComfyExtension, io
 
-class LotusConditioning:
+
+class LotusConditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-            },
-        }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LotusConditioning",
+            category="conditioning/lotus",
+            inputs=[],
+            outputs=[io.Conditioning.Output(display_name="conditioning")],
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    RETURN_NAMES = ("conditioning",)
-    FUNCTION = "conditioning"
-    CATEGORY = "conditioning/lotus"
-
-    def conditioning(self):
+    @classmethod
+    def execute(cls) -> io.NodeOutput:
         device = mm.get_torch_device()
         #lotus uses a frozen encoder and null conditioning, i'm just inlining the results of that operation since it doesn't change
         #and getting parity with the reference implementation would otherwise require inference and 800mb of tensors
@@ -22,8 +24,16 @@ class LotusConditioning:
 
         cond = [[prompt_embeds, {}]]
 
-        return (cond,)
+        return io.NodeOutput(cond)
 
-NODE_CLASS_MAPPINGS = {
-    "LotusConditioning" : LotusConditioning,
-}
+
+class LotusExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            LotusConditioning,
+        ]
+
+
+async def comfy_entrypoint() -> LotusExtension:
+    return LotusExtension()

comfy_extras/nodes_lt.py

@@ -1,4 +1,3 @@
-import io
 import nodes
 import node_helpers
 import torch
@@ -8,46 +7,60 @@ import comfy.utils
 import math
 import numpy as np
 import av
+from io import BytesIO
+from typing_extensions import override
 from comfy.ldm.lightricks.symmetric_patchifier import SymmetricPatchifier, latent_to_pixel_coords
+from comfy_api.latest import ComfyExtension, io
 
-class EmptyLTXVLatentVideo:
+class EmptyLTXVLatentVideo(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "width": ("INT", {"default": 768, "min": 64, "max": nodes.MAX_RESOLUTION, "step": 32}),
-                              "height": ("INT", {"default": 512, "min": 64, "max": nodes.MAX_RESOLUTION, "step": 32}),
-                              "length": ("INT", {"default": 97, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096})}}
-    RETURN_TYPES = ("LATENT",)
-    FUNCTION = "generate"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyLTXVLatentVideo",
+            category="latent/video/ltxv",
+            inputs=[
+                io.Int.Input("width", default=768, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("height", default=512, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("length", default=97, min=1, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
 
-    CATEGORY = "latent/video/ltxv"
-
-    def generate(self, width, height, length, batch_size=1):
+    @classmethod
+    def execute(cls, width, height, length, batch_size=1) -> io.NodeOutput:
         latent = torch.zeros([batch_size, 128, ((length - 1) // 8) + 1, height // 32, width // 32], device=comfy.model_management.intermediate_device())
-        return ({"samples": latent}, )
+        return io.NodeOutput({"samples": latent})
 
 
-class LTXVImgToVideo:
+class LTXVImgToVideo(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"positive": ("CONDITIONING", ),
-                             "negative": ("CONDITIONING", ),
-                             "vae": ("VAE",),
-                             "image": ("IMAGE",),
-                             "width": ("INT", {"default": 768, "min": 64, "max": nodes.MAX_RESOLUTION, "step": 32}),
-                             "height": ("INT", {"default": 512, "min": 64, "max": nodes.MAX_RESOLUTION, "step": 32}),
-                             "length": ("INT", {"default": 97, "min": 9, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                             "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                             "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0}),
-                             }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVImgToVideo",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Image.Input("image"),
+                io.Int.Input("width", default=768, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("height", default=512, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("length", default=97, min=9, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("strength", default=1.0, min=0.0, max=1.0),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
-
-    CATEGORY = "conditioning/video_models"
-    FUNCTION = "generate"
-
-    def generate(self, positive, negative, image, vae, width, height, length, batch_size, strength):
+    @classmethod
+    def execute(cls, positive, negative, image, vae, width, height, length, batch_size, strength) -> io.NodeOutput:
         pixels = comfy.utils.common_upscale(image.movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
         encode_pixels = pixels[:, :, :, :3]
         t = vae.encode(encode_pixels)
@@ -62,7 +75,7 @@ class LTXVImgToVideo:
         )
         conditioning_latent_frames_mask[:, :, :t.shape[2]] = 1.0 - strength
 
-        return (positive, negative, {"samples": latent, "noise_mask": conditioning_latent_frames_mask}, )
+        return io.NodeOutput(positive, negative, {"samples": latent, "noise_mask": conditioning_latent_frames_mask})
 
 
 def conditioning_get_any_value(conditioning, key, default=None):
@@ -93,35 +106,46 @@ def get_keyframe_idxs(cond):
     num_keyframes = torch.unique(keyframe_idxs[:, 0]).shape[0]
     return keyframe_idxs, num_keyframes
 
-class LTXVAddGuide:
+class LTXVAddGuide(io.ComfyNode):
+    NUM_PREFIX_FRAMES = 2
+    PATCHIFIER = SymmetricPatchifier(1)
+
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"positive": ("CONDITIONING", ),
-                             "negative": ("CONDITIONING", ),
-                             "vae": ("VAE",),
-                             "latent": ("LATENT",),
-                             "image": ("IMAGE", {"tooltip": "Image or video to condition the latent video on. Must be 8*n + 1 frames."
-                                                 "If the video is not 8*n + 1 frames, it will be cropped to the nearest 8*n + 1 frames."}),
-                             "frame_idx": ("INT", {"default": 0, "min": -9999, "max": 9999,
-                                                   "tooltip": "Frame index to start the conditioning at. For single-frame images or "
-                                                   "videos with 1-8 frames, any frame_idx value is acceptable. For videos with 9+ "
-                                                   "frames, frame_idx must be divisible by 8, otherwise it will be rounded down to "
-                                                   "the nearest multiple of 8. Negative values are counted from the end of the video."}),
-                             "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
-                             }
-            }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVAddGuide",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Latent.Input("latent"),
+                io.Image.Input(
+                    "image",
+                    tooltip="Image or video to condition the latent video on. Must be 8*n + 1 frames. "
+                            "If the video is not 8*n + 1 frames, it will be cropped to the nearest 8*n + 1 frames.",
+                ),
+                io.Int.Input(
+                    "frame_idx",
+                    default=0,
+                    min=-9999,
+                    max=9999,
+                    tooltip="Frame index to start the conditioning at. "
+                            "For single-frame images or videos with 1-8 frames, any frame_idx value is acceptable. "
+                            "For videos with 9+ frames, frame_idx must be divisible by 8, otherwise it will be rounded "
+                            "down to the nearest multiple of 8. Negative values are counted from the end of the video.",
+                ),
+                io.Float.Input("strength", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
-
-    CATEGORY = "conditioning/video_models"
-    FUNCTION = "generate"
-
-    def __init__(self):
-        self._num_prefix_frames = 2
-        self._patchifier = SymmetricPatchifier(1)
-
-    def encode(self, vae, latent_width, latent_height, images, scale_factors):
+    @classmethod
+    def encode(cls, vae, latent_width, latent_height, images, scale_factors):
         time_scale_factor, width_scale_factor, height_scale_factor = scale_factors
         images = images[:(images.shape[0] - 1) // time_scale_factor * time_scale_factor + 1]
         pixels = comfy.utils.common_upscale(images.movedim(-1, 1), latent_width * width_scale_factor, latent_height * height_scale_factor, "bilinear", crop="disabled").movedim(1, -1)
@@ -129,7 +153,8 @@ class LTXVAddGuide:
         t = vae.encode(encode_pixels)
         return encode_pixels, t
 
-    def get_latent_index(self, cond, latent_length, guide_length, frame_idx, scale_factors):
+    @classmethod
+    def get_latent_index(cls, cond, latent_length, guide_length, frame_idx, scale_factors):
         time_scale_factor, _, _ = scale_factors
         _, num_keyframes = get_keyframe_idxs(cond)
         latent_count = latent_length - num_keyframes
@@ -141,9 +166,10 @@ class LTXVAddGuide:
 
         return frame_idx, latent_idx
 
-    def add_keyframe_index(self, cond, frame_idx, guiding_latent, scale_factors):
+    @classmethod
+    def add_keyframe_index(cls, cond, frame_idx, guiding_latent, scale_factors):
         keyframe_idxs, _ = get_keyframe_idxs(cond)
-        _, latent_coords = self._patchifier.patchify(guiding_latent)
+        _, latent_coords = cls.PATCHIFIER.patchify(guiding_latent)
         pixel_coords = latent_to_pixel_coords(latent_coords, scale_factors, causal_fix=frame_idx == 0)  # we need the causal fix only if we're placing the new latents at index 0
         pixel_coords[:, 0] += frame_idx
         if keyframe_idxs is None:
@@ -152,8 +178,9 @@ class LTXVAddGuide:
             keyframe_idxs = torch.cat([keyframe_idxs, pixel_coords], dim=2)
         return node_helpers.conditioning_set_values(cond, {"keyframe_idxs": keyframe_idxs})
 
-    def append_keyframe(self, positive, negative, frame_idx, latent_image, noise_mask, guiding_latent, strength, scale_factors):
-        _, latent_idx = self.get_latent_index(
+    @classmethod
+    def append_keyframe(cls, positive, negative, frame_idx, latent_image, noise_mask, guiding_latent, strength, scale_factors):
+        _, latent_idx = cls.get_latent_index(
             cond=positive,
             latent_length=latent_image.shape[2],
             guide_length=guiding_latent.shape[2],
@@ -162,8 +189,8 @@ class LTXVAddGuide:
         )
         noise_mask[:, :, latent_idx:latent_idx + guiding_latent.shape[2]] = 1.0
 
-        positive = self.add_keyframe_index(positive, frame_idx, guiding_latent, scale_factors)
-        negative = self.add_keyframe_index(negative, frame_idx, guiding_latent, scale_factors)
+        positive = cls.add_keyframe_index(positive, frame_idx, guiding_latent, scale_factors)
+        negative = cls.add_keyframe_index(negative, frame_idx, guiding_latent, scale_factors)
 
         mask = torch.full(
             (noise_mask.shape[0], 1, guiding_latent.shape[2], noise_mask.shape[3], noise_mask.shape[4]),
@@ -176,7 +203,8 @@ class LTXVAddGuide:
         noise_mask = torch.cat([noise_mask, mask], dim=2)
         return positive, negative, latent_image, noise_mask
 
-    def replace_latent_frames(self, latent_image, noise_mask, guiding_latent, latent_idx, strength):
+    @classmethod
+    def replace_latent_frames(cls, latent_image, noise_mask, guiding_latent, latent_idx, strength):
         cond_length = guiding_latent.shape[2]
         assert latent_image.shape[2] >= latent_idx + cond_length, "Conditioning frames exceed the length of the latent sequence."
 
@@ -195,20 +223,21 @@ class LTXVAddGuide:
 
         return latent_image, noise_mask
 
-    def generate(self, positive, negative, vae, latent, image, frame_idx, strength):
+    @classmethod
+    def execute(cls, positive, negative, vae, latent, image, frame_idx, strength) -> io.NodeOutput:
         scale_factors = vae.downscale_index_formula
         latent_image = latent["samples"]
         noise_mask = get_noise_mask(latent)
 
         _, _, latent_length, latent_height, latent_width = latent_image.shape
-        image, t = self.encode(vae, latent_width, latent_height, image, scale_factors)
+        image, t = cls.encode(vae, latent_width, latent_height, image, scale_factors)
 
-        frame_idx, latent_idx = self.get_latent_index(positive, latent_length, len(image), frame_idx, scale_factors)
+        frame_idx, latent_idx = cls.get_latent_index(positive, latent_length, len(image), frame_idx, scale_factors)
         assert latent_idx + t.shape[2] <= latent_length, "Conditioning frames exceed the length of the latent sequence."
 
-        num_prefix_frames = min(self._num_prefix_frames, t.shape[2])
+        num_prefix_frames = min(cls.NUM_PREFIX_FRAMES, t.shape[2])
 
-        positive, negative, latent_image, noise_mask = self.append_keyframe(
+        positive, negative, latent_image, noise_mask = cls.append_keyframe(
             positive,
             negative,
             frame_idx,
@@ -223,9 +252,9 @@ class LTXVAddGuide:
 
         t = t[:, :, num_prefix_frames:]
         if t.shape[2] == 0:
-            return (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
+            return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
 
-        latent_image, noise_mask = self.replace_latent_frames(
+        latent_image, noise_mask = cls.replace_latent_frames(
             latent_image,
             noise_mask,
             t,
@@ -233,34 +262,35 @@ class LTXVAddGuide:
             strength,
         )
 
-        return (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
+        return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
 
 
-class LTXVCropGuides:
+class LTXVCropGuides(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"positive": ("CONDITIONING", ),
-                             "negative": ("CONDITIONING", ),
-                             "latent": ("LATENT",),
-                             }
-            }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVCropGuides",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Latent.Input("latent"),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
-
-    CATEGORY = "conditioning/video_models"
-    FUNCTION = "crop"
-
-    def __init__(self):
-        self._patchifier = SymmetricPatchifier(1)
-
-    def crop(self, positive, negative, latent):
+    @classmethod
+    def execute(cls, positive, negative, latent) -> io.NodeOutput:
         latent_image = latent["samples"].clone()
         noise_mask = get_noise_mask(latent)
 
         _, num_keyframes = get_keyframe_idxs(positive)
         if num_keyframes == 0:
-            return (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
+            return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
 
         latent_image = latent_image[:, :, :-num_keyframes]
         noise_mask = noise_mask[:, :, :-num_keyframes]
@@ -268,44 +298,52 @@ class LTXVCropGuides:
         positive = node_helpers.conditioning_set_values(positive, {"keyframe_idxs": None})
         negative = node_helpers.conditioning_set_values(negative, {"keyframe_idxs": None})
 
-        return (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
+        return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
 
 
-class LTXVConditioning:
+class LTXVConditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"positive": ("CONDITIONING", ),
-                             "negative": ("CONDITIONING", ),
-                             "frame_rate": ("FLOAT", {"default": 25.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
-                             }}
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING")
-    RETURN_NAMES = ("positive", "negative")
-    FUNCTION = "append"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVConditioning",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Float.Input("frame_rate", default=25.0, min=0.0, max=1000.0, step=0.01),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+            ],
+        )
 
-    CATEGORY = "conditioning/video_models"
-
-    def append(self, positive, negative, frame_rate):
+    @classmethod
+    def execute(cls, positive, negative, frame_rate) -> io.NodeOutput:
         positive = node_helpers.conditioning_set_values(positive, {"frame_rate": frame_rate})
         negative = node_helpers.conditioning_set_values(negative, {"frame_rate": frame_rate})
-        return (positive, negative)
+        return io.NodeOutput(positive, negative)
 
 
-class ModelSamplingLTXV:
+class ModelSamplingLTXV(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                              "max_shift": ("FLOAT", {"default": 2.05, "min": 0.0, "max": 100.0, "step":0.01}),
-                              "base_shift": ("FLOAT", {"default": 0.95, "min": 0.0, "max": 100.0, "step":0.01}),
-                              },
-                "optional": {"latent": ("LATENT",), }
-                }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingLTXV",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("max_shift", default=2.05, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("base_shift", default=0.95, min=0.0, max=100.0, step=0.01),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
-
-    CATEGORY = "advanced/model"
-
-    def patch(self, model, max_shift, base_shift, latent=None):
+    @classmethod
+    def execute(cls, model, max_shift, base_shift, latent=None) -> io.NodeOutput:
         m = model.clone()
 
         if latent is None:
@@ -329,37 +367,41 @@ class ModelSamplingLTXV:
         model_sampling.set_parameters(shift=shift)
         m.add_object_patch("model_sampling", model_sampling)
 
-        return (m, )
+        return io.NodeOutput(m)
 
 
-class LTXVScheduler:
+class LTXVScheduler(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
-                     "max_shift": ("FLOAT", {"default": 2.05, "min": 0.0, "max": 100.0, "step":0.01}),
-                     "base_shift": ("FLOAT", {"default": 0.95, "min": 0.0, "max": 100.0, "step":0.01}),
-                     "stretch": ("BOOLEAN", {
-                        "default": True,
-                        "tooltip": "Stretch the sigmas to be in the range [terminal, 1]."
-                    }),
-                     "terminal": (
-                        "FLOAT",
-                        {
-                            "default": 0.1, "min": 0.0, "max": 0.99, "step": 0.01,
-                            "tooltip": "The terminal value of the sigmas after stretching."
-                        },
-                    ),
-                    },
-                "optional": {"latent": ("LATENT",), }
-               }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVScheduler",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Int.Input("steps", default=20, min=1, max=10000),
+                io.Float.Input("max_shift", default=2.05, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("base_shift", default=0.95, min=0.0, max=100.0, step=0.01),
+                io.Boolean.Input(
+                    id="stretch",
+                    default=True,
+                    tooltip="Stretch the sigmas to be in the range [terminal, 1].",
+                ),
+                io.Float.Input(
+                    id="terminal",
+                    default=0.1,
+                    min=0.0,
+                    max=0.99,
+                    step=0.01,
+                    tooltip="The terminal value of the sigmas after stretching.",
+                ),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("SIGMAS",)
-    CATEGORY = "sampling/custom_sampling/schedulers"
-
-    FUNCTION = "get_sigmas"
-
-    def get_sigmas(self, steps, max_shift, base_shift, stretch, terminal, latent=None):
+    @classmethod
+    def execute(cls, steps, max_shift, base_shift, stretch, terminal, latent=None) -> io.NodeOutput:
         if latent is None:
             tokens = 4096
         else:
@@ -389,7 +431,7 @@ class LTXVScheduler:
             stretched = 1.0 - (one_minus_z / scale_factor)
             sigmas[non_zero_mask] = stretched
 
-        return (sigmas,)
+        return io.NodeOutput(sigmas)
 
 def encode_single_frame(output_file, image_array: np.ndarray, crf):
     container = av.open(output_file, "w", format="mp4")
@@ -423,52 +465,54 @@ def preprocess(image: torch.Tensor, crf=29):
         return image
 
     image_array = (image[:(image.shape[0] // 2) * 2, :(image.shape[1] // 2) * 2] * 255.0).byte().cpu().numpy()
-    with io.BytesIO() as output_file:
+    with BytesIO() as output_file:
         encode_single_frame(output_file, image_array, crf)
         video_bytes = output_file.getvalue()
-    with io.BytesIO(video_bytes) as video_file:
+    with BytesIO(video_bytes) as video_file:
         image_array = decode_single_frame(video_file)
     tensor = torch.tensor(image_array, dtype=image.dtype, device=image.device) / 255.0
     return tensor
 
 
-class LTXVPreprocess:
+class LTXVPreprocess(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "img_compression": (
-                    "INT",
-                    {
-                        "default": 35,
-                        "min": 0,
-                        "max": 100,
-                        "tooltip": "Amount of compression to apply on image.",
-                    },
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVPreprocess",
+            category="image",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input(
+                    id="img_compression", default=35, min=0, max=100, tooltip="Amount of compression to apply on image."
                 ),
-            }
-        }
+            ],
+            outputs=[
+                io.Image.Output(display_name="output_image"),
+            ],
+        )
 
-    FUNCTION = "preprocess"
-    RETURN_TYPES = ("IMAGE",)
-    RETURN_NAMES = ("output_image",)
-    CATEGORY = "image"
-
-    def preprocess(self, image, img_compression):
+    @classmethod
+    def execute(cls, image, img_compression) -> io.NodeOutput:
         output_images = []
         for i in range(image.shape[0]):
             output_images.append(preprocess(image[i], img_compression))
-        return (torch.stack(output_images),)
+        return io.NodeOutput(torch.stack(output_images))
 
 
-NODE_CLASS_MAPPINGS = {
-    "EmptyLTXVLatentVideo": EmptyLTXVLatentVideo,
-    "LTXVImgToVideo": LTXVImgToVideo,
-    "ModelSamplingLTXV": ModelSamplingLTXV,
-    "LTXVConditioning": LTXVConditioning,
-    "LTXVScheduler": LTXVScheduler,
-    "LTXVAddGuide": LTXVAddGuide,
-    "LTXVPreprocess": LTXVPreprocess,
-    "LTXVCropGuides": LTXVCropGuides,
-}
+class LtxvExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            EmptyLTXVLatentVideo,
+            LTXVImgToVideo,
+            ModelSamplingLTXV,
+            LTXVConditioning,
+            LTXVScheduler,
+            LTXVAddGuide,
+            LTXVPreprocess,
+            LTXVCropGuides,
+        ]
+
+
+async def comfy_entrypoint() -> LtxvExtension:
+    return LtxvExtension()

comfy_extras/nodes_lumina2.py

@@ -1,20 +1,27 @@
-from comfy.comfy_types import IO, ComfyNodeABC, InputTypeDict
+from typing_extensions import override
 import torch
 
+from comfy_api.latest import ComfyExtension, io
 
-class RenormCFG:
+
+class RenormCFG(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                              "cfg_trunc": ("FLOAT", {"default": 100, "min": 0.0, "max": 100.0, "step": 0.01}),
-                              "renorm_cfg": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 100.0, "step": 0.01}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RenormCFG",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("cfg_trunc", default=100, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("renorm_cfg", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    CATEGORY = "advanced/model"
-
-    def patch(self, model, cfg_trunc, renorm_cfg):
+    @classmethod
+    def execute(cls, model, cfg_trunc, renorm_cfg) -> io.NodeOutput:
         def renorm_cfg_func(args):
             cond_denoised = args["cond_denoised"]
             uncond_denoised = args["uncond_denoised"]
@@ -53,10 +60,10 @@ class RenormCFG:
 
         m = model.clone()
         m.set_model_sampler_cfg_function(renorm_cfg_func)
-        return (m, )
+        return io.NodeOutput(m)
 
 
-class CLIPTextEncodeLumina2(ComfyNodeABC):
+class CLIPTextEncodeLumina2(io.ComfyNode):
     SYSTEM_PROMPT = {
         "superior": "You are an assistant designed to generate superior images with the superior "\
             "degree of image-text alignment based on textual prompts or user prompts.",
@@ -69,36 +76,52 @@ class CLIPTextEncodeLumina2(ComfyNodeABC):
         "Alignment: You are an assistant designed to generate high-quality images with the highest "\
         "degree of image-text alignment based on textual prompts."
     @classmethod
-    def INPUT_TYPES(s) -> InputTypeDict:
-        return {
-            "required": {
-                "system_prompt": (list(CLIPTextEncodeLumina2.SYSTEM_PROMPT.keys()), {"tooltip": CLIPTextEncodeLumina2.SYSTEM_PROMPT_TIP}),
-                "user_prompt": (IO.STRING, {"multiline": True, "dynamicPrompts": True, "tooltip": "The text to be encoded."}),
-                "clip": (IO.CLIP, {"tooltip": "The CLIP model used for encoding the text."})
-            }
-        }
-    RETURN_TYPES = (IO.CONDITIONING,)
-    OUTPUT_TOOLTIPS = ("A conditioning containing the embedded text used to guide the diffusion model.",)
-    FUNCTION = "encode"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeLumina2",
+            display_name="CLIP Text Encode for Lumina2",
+            category="conditioning",
+            description="Encodes a system prompt and a user prompt using a CLIP model into an embedding "
+                        "that can be used to guide the diffusion model towards generating specific images.",
+            inputs=[
+                io.Combo.Input(
+                    "system_prompt",
+                    options=list(cls.SYSTEM_PROMPT.keys()),
+                    tooltip=cls.SYSTEM_PROMPT_TIP,
+                ),
+                io.String.Input(
+                    "user_prompt",
+                    multiline=True,
+                    dynamic_prompts=True,
+                    tooltip="The text to be encoded.",
+                ),
+                io.Clip.Input("clip", tooltip="The CLIP model used for encoding the text."),
+            ],
+            outputs=[
+                io.Conditioning.Output(
+                    tooltip="A conditioning containing the embedded text used to guide the diffusion model.",
+                ),
+            ],
+        )
 
-    CATEGORY = "conditioning"
-    DESCRIPTION = "Encodes a system prompt and a user prompt using a CLIP model into an embedding that can be used to guide the diffusion model towards generating specific images."
-
-    def encode(self, clip, user_prompt, system_prompt):
+    @classmethod
+    def execute(cls, clip, user_prompt, system_prompt) -> io.NodeOutput:
         if clip is None:
             raise RuntimeError("ERROR: clip input is invalid: None\n\nIf the clip is from a checkpoint loader node your checkpoint does not contain a valid clip or text encoder model.")
-        system_prompt = CLIPTextEncodeLumina2.SYSTEM_PROMPT[system_prompt]
+        system_prompt = cls.SYSTEM_PROMPT[system_prompt]
         prompt = f'{system_prompt} <Prompt Start> {user_prompt}'
         tokens = clip.tokenize(prompt)
-        return (clip.encode_from_tokens_scheduled(tokens), )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
 
 
-NODE_CLASS_MAPPINGS = {
-    "CLIPTextEncodeLumina2": CLIPTextEncodeLumina2,
-    "RenormCFG": RenormCFG
-}
+class Lumina2Extension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            CLIPTextEncodeLumina2,
+            RenormCFG,
+        ]
 
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "CLIPTextEncodeLumina2": "CLIP Text Encode for Lumina2",
-}
+async def comfy_entrypoint() -> Lumina2Extension:
+    return Lumina2Extension()

comfy_extras/nodes_mahiro.py

@@ -1,17 +1,29 @@
+from typing_extensions import override
 import torch
 import torch.nn.functional as F
 
-class Mahiro:
+from comfy_api.latest import ComfyExtension, io
+
+
+class Mahiro(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"model": ("MODEL",),
-                            }}
-    RETURN_TYPES = ("MODEL",)
-    RETURN_NAMES = ("patched_model",)
-    FUNCTION = "patch"
-    CATEGORY = "_for_testing"
-    DESCRIPTION = "Modify the guidance to scale more on the 'direction' of the positive prompt rather than the difference between the negative prompt."
-    def patch(self, model):
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Mahiro",
+            display_name="Mahiro is so cute that she deserves a better guidance function!! (。・ω・。)",
+            category="_for_testing",
+            description="Modify the guidance to scale more on the 'direction' of the positive prompt rather than the difference between the negative prompt.",
+            inputs=[
+                io.Model.Input("model"),
+            ],
+            outputs=[
+                io.Model.Output(display_name="patched_model"),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model) -> io.NodeOutput:
         m = model.clone()
         def mahiro_normd(args):
             scale: float = args['cond_scale']
@@ -30,12 +42,16 @@ class Mahiro:
             wm = (simsc*cfg + (4-simsc)*leap) / 4
             return wm
         m.set_model_sampler_post_cfg_function(mahiro_normd)
-        return (m, )
+        return io.NodeOutput(m)
 
-NODE_CLASS_MAPPINGS = {
-    "Mahiro": Mahiro
-}
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "Mahiro": "Mahiro is so cute that she deserves a better guidance function!! (。・ω・。)",
-}
+class MahiroExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            Mahiro,
+        ]
+
+
+async def comfy_entrypoint() -> MahiroExtension:
+    return MahiroExtension()

comfy_extras/nodes_mask.py

@@ -12,35 +12,38 @@ from nodes import MAX_RESOLUTION
 def composite(destination, source, x, y, mask = None, multiplier = 8, resize_source = False):
     source = source.to(destination.device)
     if resize_source:
-        source = torch.nn.functional.interpolate(source, size=(destination.shape[2], destination.shape[3]), mode="bilinear")
+        source = torch.nn.functional.interpolate(source, size=(destination.shape[-2], destination.shape[-1]), mode="bilinear")
 
     source = comfy.utils.repeat_to_batch_size(source, destination.shape[0])
 
-    x = max(-source.shape[3] * multiplier, min(x, destination.shape[3] * multiplier))
-    y = max(-source.shape[2] * multiplier, min(y, destination.shape[2] * multiplier))
+    x = max(-source.shape[-1] * multiplier, min(x, destination.shape[-1] * multiplier))
+    y = max(-source.shape[-2] * multiplier, min(y, destination.shape[-2] * multiplier))
 
     left, top = (x // multiplier, y // multiplier)
-    right, bottom = (left + source.shape[3], top + source.shape[2],)
+    right, bottom = (left + source.shape[-1], top + source.shape[-2],)
 
     if mask is None:
         mask = torch.ones_like(source)
     else:
         mask = mask.to(destination.device, copy=True)
-        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(source.shape[2], source.shape[3]), mode="bilinear")
+        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(source.shape[-2], source.shape[-1]), mode="bilinear")
         mask = comfy.utils.repeat_to_batch_size(mask, source.shape[0])
 
     # calculate the bounds of the source that will be overlapping the destination
     # this prevents the source trying to overwrite latent pixels that are out of bounds
     # of the destination
-    visible_width, visible_height = (destination.shape[3] - left + min(0, x), destination.shape[2] - top + min(0, y),)
+    visible_width, visible_height = (destination.shape[-1] - left + min(0, x), destination.shape[-2] - top + min(0, y),)
 
     mask = mask[:, :, :visible_height, :visible_width]
+    if mask.ndim < source.ndim:
+        mask = mask.unsqueeze(1)
+
     inverse_mask = torch.ones_like(mask) - mask
 
-    source_portion = mask * source[:, :, :visible_height, :visible_width]
-    destination_portion = inverse_mask  * destination[:, :, top:bottom, left:right]
+    source_portion = mask * source[..., :visible_height, :visible_width]
+    destination_portion = inverse_mask  * destination[..., top:bottom, left:right]
 
-    destination[:, :, top:bottom, left:right] = source_portion + destination_portion
+    destination[..., top:bottom, left:right] = source_portion + destination_portion
     return destination
 
 class LatentCompositeMasked:

comfy_extras/nodes_mochi.py

@@ -1,23 +1,40 @@
-import nodes
+from typing_extensions import override
 import torch
 import comfy.model_management
+import nodes
+from comfy_api.latest import ComfyExtension, io
 
-class EmptyMochiLatentVideo:
+
+class EmptyMochiLatentVideo(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "width": ("INT", {"default": 848, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
-                              "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
-                              "length": ("INT", {"default": 25, "min": 7, "max": nodes.MAX_RESOLUTION, "step": 6}),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096})}}
-    RETURN_TYPES = ("LATENT",)
-    FUNCTION = "generate"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyMochiLatentVideo",
+            category="latent/video",
+            inputs=[
+                io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=25, min=7, max=nodes.MAX_RESOLUTION, step=6),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
 
-    CATEGORY = "latent/video"
-
-    def generate(self, width, height, length, batch_size=1):
+    @classmethod
+    def execute(cls, width, height, length, batch_size=1) -> io.NodeOutput:
         latent = torch.zeros([batch_size, 12, ((length - 1) // 6) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
-        return ({"samples":latent}, )
+        return io.NodeOutput({"samples": latent})
 
-NODE_CLASS_MAPPINGS = {
-    "EmptyMochiLatentVideo": EmptyMochiLatentVideo,
-}
+
+class MochiExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            EmptyMochiLatentVideo,
+        ]
+
+
+async def comfy_entrypoint() -> MochiExtension:
+    return MochiExtension()

comfy_extras/nodes_morphology.py

@@ -1,24 +1,34 @@
 import torch
 import comfy.model_management
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 from kornia.morphology import dilation, erosion, opening, closing, gradient, top_hat, bottom_hat
 import kornia.color
 
 
-class Morphology:
+class Morphology(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"image": ("IMAGE",),
-                                "operation": (["erode",  "dilate", "open", "close", "gradient", "bottom_hat", "top_hat"],),
-                                "kernel_size": ("INT", {"default": 3, "min": 3, "max": 999, "step": 1}),
-                                }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Morphology",
+            display_name="ImageMorphology",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input(
+                    "operation",
+                    options=["erode", "dilate", "open", "close", "gradient", "bottom_hat", "top_hat"],
+                ),
+                io.Int.Input("kernel_size", default=3, min=3, max=999, step=1),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "process"
-
-    CATEGORY = "image/postprocessing"
-
-    def process(self, image, operation, kernel_size):
+    @classmethod
+    def execute(cls, image, operation, kernel_size) -> io.NodeOutput:
         device = comfy.model_management.get_torch_device()
         kernel = torch.ones(kernel_size, kernel_size, device=device)
         image_k = image.to(device).movedim(-1, 1)
@@ -39,49 +49,63 @@ class Morphology:
         else:
             raise ValueError(f"Invalid operation {operation} for morphology. Must be one of 'erode', 'dilate', 'open', 'close', 'gradient', 'tophat', 'bottomhat'")
         img_out = output.to(comfy.model_management.intermediate_device()).movedim(1, -1)
-        return (img_out,)
+        return io.NodeOutput(img_out)
 
 
-class ImageRGBToYUV:
+class ImageRGBToYUV(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",),
-                              }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageRGBToYUV",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("image"),
+            ],
+            outputs=[
+                io.Image.Output(display_name="Y"),
+                io.Image.Output(display_name="U"),
+                io.Image.Output(display_name="V"),
+            ],
+        )
 
-    RETURN_TYPES = ("IMAGE", "IMAGE", "IMAGE")
-    RETURN_NAMES = ("Y", "U", "V")
-    FUNCTION = "execute"
-
-    CATEGORY = "image/batch"
-
-    def execute(self, image):
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
         out = kornia.color.rgb_to_ycbcr(image.movedim(-1, 1)).movedim(1, -1)
-        return (out[..., 0:1].expand_as(image), out[..., 1:2].expand_as(image), out[..., 2:3].expand_as(image))
+        return io.NodeOutput(out[..., 0:1].expand_as(image), out[..., 1:2].expand_as(image), out[..., 2:3].expand_as(image))
 
-class ImageYUVToRGB:
+class ImageYUVToRGB(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"Y": ("IMAGE",),
-                             "U": ("IMAGE",),
-                             "V": ("IMAGE",),
-                              }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageYUVToRGB",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("Y"),
+                io.Image.Input("U"),
+                io.Image.Input("V"),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "execute"
-
-    CATEGORY = "image/batch"
-
-    def execute(self, Y, U, V):
+    @classmethod
+    def execute(cls, Y, U, V) -> io.NodeOutput:
         image = torch.cat([torch.mean(Y, dim=-1, keepdim=True), torch.mean(U, dim=-1, keepdim=True), torch.mean(V, dim=-1, keepdim=True)], dim=-1)
         out = kornia.color.ycbcr_to_rgb(image.movedim(-1, 1)).movedim(1, -1)
-        return (out,)
+        return io.NodeOutput(out)
 
-NODE_CLASS_MAPPINGS = {
-    "Morphology": Morphology,
-    "ImageRGBToYUV": ImageRGBToYUV,
-    "ImageYUVToRGB": ImageYUVToRGB,
-}
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "Morphology": "ImageMorphology",
-}
+class MorphologyExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            Morphology,
+            ImageRGBToYUV,
+            ImageYUVToRGB,
+        ]
+
+
+async def comfy_entrypoint() -> MorphologyExtension:
+    return MorphologyExtension()
+

comfy_extras/nodes_optimalsteps.py

@@ -1,9 +1,12 @@
 # from https://github.com/bebebe666/OptimalSteps
 
-
 import numpy as np
 import torch
 
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
+
+
 def loglinear_interp(t_steps, num_steps):
     """
     Performs log-linear interpolation of a given array of decreasing numbers.
@@ -23,25 +26,28 @@ NOISE_LEVELS = {"FLUX": [0.9968, 0.9886, 0.9819, 0.975, 0.966, 0.9471, 0.9158, 0
 "Chroma": [0.992, 0.99, 0.988, 0.985, 0.982, 0.978, 0.973, 0.968, 0.961, 0.953, 0.943, 0.931, 0.917, 0.9, 0.881, 0.858, 0.832, 0.802, 0.769, 0.731, 0.69, 0.646, 0.599, 0.55, 0.501, 0.451, 0.402, 0.355, 0.311, 0.27, 0.232, 0.199, 0.169, 0.143, 0.12, 0.101, 0.084, 0.07, 0.058, 0.048, 0.001],
 }
 
-class OptimalStepsScheduler:
+class OptimalStepsScheduler(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"model_type": (["FLUX", "Wan", "Chroma"], ),
-                     "steps": ("INT", {"default": 20, "min": 3, "max": 1000}),
-                     "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
-                      }
-               }
-    RETURN_TYPES = ("SIGMAS",)
-    CATEGORY = "sampling/custom_sampling/schedulers"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="OptimalStepsScheduler",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Combo.Input("model_type", options=["FLUX", "Wan", "Chroma"]),
+                io.Int.Input("steps", default=20, min=3, max=1000),
+                io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
 
-    FUNCTION = "get_sigmas"
-
-    def get_sigmas(self, model_type, steps, denoise):
+    @classmethod
+    def execute(cls, model_type, steps, denoise) ->io.NodeOutput:
         total_steps = steps
         if denoise < 1.0:
             if denoise <= 0.0:
-                return (torch.FloatTensor([]),)
+                return io.NodeOutput(torch.FloatTensor([]))
             total_steps = round(steps * denoise)
 
         sigmas = NOISE_LEVELS[model_type][:]
@@ -50,8 +56,16 @@ class OptimalStepsScheduler:
 
         sigmas = sigmas[-(total_steps + 1):]
         sigmas[-1] = 0
-        return (torch.FloatTensor(sigmas), )
+        return io.NodeOutput(torch.FloatTensor(sigmas))
 
-NODE_CLASS_MAPPINGS = {
-    "OptimalStepsScheduler": OptimalStepsScheduler,
-}
+
+class OptimalStepsExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            OptimalStepsScheduler,
+        ]
+
+
+async def comfy_entrypoint() -> OptimalStepsExtension:
+    return OptimalStepsExtension()

comfy_extras/nodes_pag.py

@@ -3,25 +3,30 @@
 
 #My modified one here is more basic but has less chances of breaking with ComfyUI updates.
 
+from typing_extensions import override
+
 import comfy.model_patcher
 import comfy.samplers
+from comfy_api.latest import ComfyExtension, io
 
-class PerturbedAttentionGuidance:
+
+class PerturbedAttentionGuidance(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "model": ("MODEL",),
-                "scale": ("FLOAT", {"default": 3.0, "min": 0.0, "max": 100.0, "step": 0.01, "round": 0.01}),
-            }
-        }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PerturbedAttentionGuidance",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale", default=3.0, min=0.0, max=100.0, step=0.01, round=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
-
-    CATEGORY = "model_patches/unet"
-
-    def patch(self, model, scale):
+    @classmethod
+    def execute(cls, model, scale) -> io.NodeOutput:
         unet_block = "middle"
         unet_block_id = 0
         m = model.clone()
@@ -49,8 +54,16 @@ class PerturbedAttentionGuidance:
 
         m.set_model_sampler_post_cfg_function(post_cfg_function)
 
-        return (m,)
+        return io.NodeOutput(m)
 
-NODE_CLASS_MAPPINGS = {
-    "PerturbedAttentionGuidance": PerturbedAttentionGuidance,
-}
+
+class PAGExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            PerturbedAttentionGuidance,
+        ]
+
+
+async def comfy_entrypoint() -> PAGExtension:
+    return PAGExtension()

comfy_extras/nodes_perpneg.py

@@ -5,6 +5,9 @@ import comfy.samplers
 import comfy.utils
 import node_helpers
 import math
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
+
 
 def perp_neg(x, noise_pred_pos, noise_pred_neg, noise_pred_nocond, neg_scale, cond_scale):
     pos = noise_pred_pos - noise_pred_nocond
@@ -16,20 +19,27 @@ def perp_neg(x, noise_pred_pos, noise_pred_neg, noise_pred_nocond, neg_scale, co
     return cfg_result
 
 #TODO: This node should be removed, it has been replaced with PerpNegGuider
-class PerpNeg:
+class PerpNeg(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {"model": ("MODEL", ),
-                             "empty_conditioning": ("CONDITIONING", ),
-                             "neg_scale": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 100.0, "step": 0.01}),
-                            }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PerpNeg",
+            display_name="Perp-Neg (DEPRECATED by PerpNegGuider)",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Conditioning.Input("empty_conditioning"),
+                io.Float.Input("neg_scale", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+            is_deprecated=True,
+        )
 
-    CATEGORY = "_for_testing"
-    DEPRECATED = True
-
-    def patch(self, model, empty_conditioning, neg_scale):
+    @classmethod
+    def execute(cls, model, empty_conditioning, neg_scale) -> io.NodeOutput:
         m = model.clone()
         nocond = comfy.sampler_helpers.convert_cond(empty_conditioning)
 
@@ -50,7 +60,7 @@ class PerpNeg:
 
         m.set_model_sampler_cfg_function(cfg_function)
 
-        return (m, )
+        return io.NodeOutput(m)
 
 
 class Guider_PerpNeg(comfy.samplers.CFGGuider):
@@ -112,35 +122,42 @@ class Guider_PerpNeg(comfy.samplers.CFGGuider):
 
         return cfg_result
 
-class PerpNegGuider:
+class PerpNegGuider(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required":
-                    {"model": ("MODEL",),
-                    "positive": ("CONDITIONING", ),
-                    "negative": ("CONDITIONING", ),
-                    "empty_conditioning": ("CONDITIONING", ),
-                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}),
-                    "neg_scale": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 100.0, "step": 0.01}),
-                     }
-                }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PerpNegGuider",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Conditioning.Input("empty_conditioning"),
+                io.Float.Input("cfg", default=8.0, min=0.0, max=100.0, step=0.1, round=0.01),
+                io.Float.Input("neg_scale", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Guider.Output(),
+            ],
+            is_experimental=True,
+        )
 
-    RETURN_TYPES = ("GUIDER",)
-
-    FUNCTION = "get_guider"
-    CATEGORY = "_for_testing"
-
-    def get_guider(self, model, positive, negative, empty_conditioning, cfg, neg_scale):
+    @classmethod
+    def execute(cls, model, positive, negative, empty_conditioning, cfg, neg_scale) -> io.NodeOutput:
         guider = Guider_PerpNeg(model)
         guider.set_conds(positive, negative, empty_conditioning)
         guider.set_cfg(cfg, neg_scale)
-        return (guider,)
+        return io.NodeOutput(guider)
 
-NODE_CLASS_MAPPINGS = {
-    "PerpNeg": PerpNeg,
-    "PerpNegGuider": PerpNegGuider,
-}
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "PerpNeg": "Perp-Neg (DEPRECATED by PerpNegGuider)",
-}
+class PerpNegExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            PerpNeg,
+            PerpNegGuider,
+        ]
+
+
+async def comfy_entrypoint() -> PerpNegExtension:
+    return PerpNegExtension()

comfy_extras/nodes_photomaker.py

@@ -4,6 +4,8 @@ import folder_paths
 import comfy.clip_model
 import comfy.clip_vision
 import comfy.ops
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 # code for model from: https://github.com/TencentARC/PhotoMaker/blob/main/photomaker/model.py under Apache License Version 2.0
 VISION_CONFIG_DICT = {
@@ -116,41 +118,52 @@ class PhotoMakerIDEncoder(comfy.clip_model.CLIPVisionModelProjection):
         return updated_prompt_embeds
 
 
-class PhotoMakerLoader:
+class PhotoMakerLoader(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "photomaker_model_name": (folder_paths.get_filename_list("photomaker"), )}}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PhotoMakerLoader",
+            category="_for_testing/photomaker",
+            inputs=[
+                io.Combo.Input("photomaker_model_name", options=folder_paths.get_filename_list("photomaker")),
+            ],
+            outputs=[
+                io.Photomaker.Output(),
+            ],
+            is_experimental=True,
+        )
 
-    RETURN_TYPES = ("PHOTOMAKER",)
-    FUNCTION = "load_photomaker_model"
-
-    CATEGORY = "_for_testing/photomaker"
-
-    def load_photomaker_model(self, photomaker_model_name):
+    @classmethod
+    def execute(cls, photomaker_model_name):
         photomaker_model_path = folder_paths.get_full_path_or_raise("photomaker", photomaker_model_name)
         photomaker_model = PhotoMakerIDEncoder()
         data = comfy.utils.load_torch_file(photomaker_model_path, safe_load=True)
         if "id_encoder" in data:
             data = data["id_encoder"]
         photomaker_model.load_state_dict(data)
-        return (photomaker_model,)
+        return io.NodeOutput(photomaker_model)
 
 
-class PhotoMakerEncode:
+class PhotoMakerEncode(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "photomaker": ("PHOTOMAKER",),
-                              "image": ("IMAGE",),
-                              "clip": ("CLIP", ),
-                              "text": ("STRING", {"multiline": True, "dynamicPrompts": True, "default": "photograph of photomaker"}),
-                             }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PhotoMakerEncode",
+            category="_for_testing/photomaker",
+            inputs=[
+                io.Photomaker.Input("photomaker"),
+                io.Image.Input("image"),
+                io.Clip.Input("clip"),
+                io.String.Input("text", multiline=True, dynamic_prompts=True, default="photograph of photomaker"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+            is_experimental=True,
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "apply_photomaker"
-
-    CATEGORY = "_for_testing/photomaker"
-
-    def apply_photomaker(self, photomaker, image, clip, text):
+    @classmethod
+    def execute(cls, photomaker, image, clip, text):
         special_token = "photomaker"
         pixel_values = comfy.clip_vision.clip_preprocess(image.to(photomaker.load_device)).float()
         try:
@@ -178,11 +191,16 @@ class PhotoMakerEncode:
         else:
             out = cond
 
-        return ([[out, {"pooled_output": pooled}]], )
+        return io.NodeOutput([[out, {"pooled_output": pooled}]])
 
 
-NODE_CLASS_MAPPINGS = {
-    "PhotoMakerLoader": PhotoMakerLoader,
-    "PhotoMakerEncode": PhotoMakerEncode,
-}
+class PhotomakerExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            PhotoMakerLoader,
+            PhotoMakerEncode,
+        ]
 
+async def comfy_entrypoint() -> PhotomakerExtension:
+    return PhotomakerExtension()

comfy_extras/nodes_pixart.py

@@ -1,24 +1,38 @@
-from nodes import MAX_RESOLUTION
+from typing_extensions import override
+import nodes
+from comfy_api.latest import ComfyExtension, io
 
-class CLIPTextEncodePixArtAlpha:
+class CLIPTextEncodePixArtAlpha(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            # "aspect_ratio": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
-            "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
-            }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodePixArtAlpha",
+            category="advanced/conditioning",
+            description="Encodes text and sets the resolution conditioning for PixArt Alpha. Does not apply to PixArt Sigma.",
+            inputs=[
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                # "aspect_ratio": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
+                io.String.Input("text", multiline=True, dynamic_prompts=True),
+                io.Clip.Input("clip"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
-    CATEGORY = "advanced/conditioning"
-    DESCRIPTION = "Encodes text and sets the resolution conditioning for PixArt Alpha. Does not apply to PixArt Sigma."
-
-    def encode(self, clip, width, height, text):
+    @classmethod
+    def execute(cls, clip, width, height, text):
         tokens = clip.tokenize(text)
-        return (clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height}),)
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height}))
 
-NODE_CLASS_MAPPINGS = {
-    "CLIPTextEncodePixArtAlpha": CLIPTextEncodePixArtAlpha,
-}
+
+class PixArtExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            CLIPTextEncodePixArtAlpha,
+        ]
+
+async def comfy_entrypoint() -> PixArtExtension:
+    return PixArtExtension()

comfy_extras/nodes_post_processing.py

@@ -1,3 +1,4 @@
+from typing_extensions import override
 import numpy as np
 import torch
 import torch.nn.functional as F
@@ -7,33 +8,27 @@ import math
 import comfy.utils
 import comfy.model_management
 import node_helpers
+from comfy_api.latest import ComfyExtension, io
 
-class Blend:
-    def __init__(self):
-        pass
+class Blend(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageBlend",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image1"),
+                io.Image.Input("image2"),
+                io.Float.Input("blend_factor", default=0.5, min=0.0, max=1.0, step=0.01),
+                io.Combo.Input("blend_mode", options=["normal", "multiply", "screen", "overlay", "soft_light", "difference"]),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image1": ("IMAGE",),
-                "image2": ("IMAGE",),
-                "blend_factor": ("FLOAT", {
-                    "default": 0.5,
-                    "min": 0.0,
-                    "max": 1.0,
-                    "step": 0.01
-                }),
-                "blend_mode": (["normal", "multiply", "screen", "overlay", "soft_light", "difference"],),
-            },
-        }
-
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "blend_images"
-
-    CATEGORY = "image/postprocessing"
-
-    def blend_images(self, image1: torch.Tensor, image2: torch.Tensor, blend_factor: float, blend_mode: str):
+    def execute(cls, image1: torch.Tensor, image2: torch.Tensor, blend_factor: float, blend_mode: str) -> io.NodeOutput:
         image1, image2 = node_helpers.image_alpha_fix(image1, image2)
         image2 = image2.to(image1.device)
         if image1.shape != image2.shape:
@@ -41,12 +36,13 @@ class Blend:
             image2 = comfy.utils.common_upscale(image2, image1.shape[2], image1.shape[1], upscale_method='bicubic', crop='center')
             image2 = image2.permute(0, 2, 3, 1)
 
-        blended_image = self.blend_mode(image1, image2, blend_mode)
+        blended_image = cls.blend_mode(image1, image2, blend_mode)
         blended_image = image1 * (1 - blend_factor) + blended_image * blend_factor
         blended_image = torch.clamp(blended_image, 0, 1)
-        return (blended_image,)
+        return io.NodeOutput(blended_image)
 
-    def blend_mode(self, img1, img2, mode):
+    @classmethod
+    def blend_mode(cls, img1, img2, mode):
         if mode == "normal":
             return img2
         elif mode == "multiply":
@@ -56,13 +52,13 @@ class Blend:
         elif mode == "overlay":
             return torch.where(img1 <= 0.5, 2 * img1 * img2, 1 - 2 * (1 - img1) * (1 - img2))
         elif mode == "soft_light":
-            return torch.where(img2 <= 0.5, img1 - (1 - 2 * img2) * img1 * (1 - img1), img1 + (2 * img2 - 1) * (self.g(img1) - img1))
+            return torch.where(img2 <= 0.5, img1 - (1 - 2 * img2) * img1 * (1 - img1), img1 + (2 * img2 - 1) * (cls.g(img1) - img1))
         elif mode == "difference":
             return img1 - img2
-        else:
-            raise ValueError(f"Unsupported blend mode: {mode}")
+        raise ValueError(f"Unsupported blend mode: {mode}")
 
-    def g(self, x):
+    @classmethod
+    def g(cls, x):
         return torch.where(x <= 0.25, ((16 * x - 12) * x + 4) * x, torch.sqrt(x))
 
 def gaussian_kernel(kernel_size: int, sigma: float, device=None):
@@ -71,38 +67,26 @@ def gaussian_kernel(kernel_size: int, sigma: float, device=None):
     g = torch.exp(-(d * d) / (2.0 * sigma * sigma))
     return g / g.sum()
 
-class Blur:
-    def __init__(self):
-        pass
+class Blur(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageBlur",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("blur_radius", default=1, min=1, max=31, step=1),
+                io.Float.Input("sigma", default=1.0, min=0.1, max=10.0, step=0.1),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "blur_radius": ("INT", {
-                    "default": 1,
-                    "min": 1,
-                    "max": 31,
-                    "step": 1
-                }),
-                "sigma": ("FLOAT", {
-                    "default": 1.0,
-                    "min": 0.1,
-                    "max": 10.0,
-                    "step": 0.1
-                }),
-            },
-        }
-
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "blur"
-
-    CATEGORY = "image/postprocessing"
-
-    def blur(self, image: torch.Tensor, blur_radius: int, sigma: float):
+    def execute(cls, image: torch.Tensor, blur_radius: int, sigma: float) -> io.NodeOutput:
         if blur_radius == 0:
-            return (image,)
+            return io.NodeOutput(image)
 
         image = image.to(comfy.model_management.get_torch_device())
         batch_size, height, width, channels = image.shape
@@ -115,31 +99,24 @@ class Blur:
         blurred = F.conv2d(padded_image, kernel, padding=kernel_size // 2, groups=channels)[:,:,blur_radius:-blur_radius, blur_radius:-blur_radius]
         blurred = blurred.permute(0, 2, 3, 1)
 
-        return (blurred.to(comfy.model_management.intermediate_device()),)
+        return io.NodeOutput(blurred.to(comfy.model_management.intermediate_device()))
 
-class Quantize:
-    def __init__(self):
-        pass
 
+class Quantize(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "colors": ("INT", {
-                    "default": 256,
-                    "min": 1,
-                    "max": 256,
-                    "step": 1
-                }),
-                "dither": (["none", "floyd-steinberg", "bayer-2", "bayer-4", "bayer-8", "bayer-16"],),
-            },
-        }
-
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "quantize"
-
-    CATEGORY = "image/postprocessing"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageQuantize",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("colors", default=256, min=1, max=256, step=1),
+                io.Combo.Input("dither", options=["none", "floyd-steinberg", "bayer-2", "bayer-4", "bayer-8", "bayer-16"]),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
     @staticmethod
     def bayer(im, pal_im, order):
@@ -167,7 +144,8 @@ class Quantize:
         im = im.quantize(palette=pal_im, dither=Image.Dither.NONE)
         return im
 
-    def quantize(self, image: torch.Tensor, colors: int, dither: str):
+    @classmethod
+    def execute(cls, image: torch.Tensor, colors: int, dither: str) -> io.NodeOutput:
         batch_size, height, width, _ = image.shape
         result = torch.zeros_like(image)
 
@@ -187,46 +165,29 @@ class Quantize:
             quantized_array = torch.tensor(np.array(quantized_image.convert("RGB"))).float() / 255
             result[b] = quantized_array
 
-        return (result,)
+        return io.NodeOutput(result)
 
-class Sharpen:
-    def __init__(self):
-        pass
+class Sharpen(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageSharpen",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("sharpen_radius", default=1, min=1, max=31, step=1),
+                io.Float.Input("sigma", default=1.0, min=0.1, max=10.0, step=0.01),
+                io.Float.Input("alpha", default=1.0, min=0.0, max=5.0, step=0.01),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "sharpen_radius": ("INT", {
-                    "default": 1,
-                    "min": 1,
-                    "max": 31,
-                    "step": 1
-                }),
-                "sigma": ("FLOAT", {
-                    "default": 1.0,
-                    "min": 0.1,
-                    "max": 10.0,
-                    "step": 0.01
-                }),
-                "alpha": ("FLOAT", {
-                    "default": 1.0,
-                    "min": 0.0,
-                    "max": 5.0,
-                    "step": 0.01
-                }),
-            },
-        }
-
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "sharpen"
-
-    CATEGORY = "image/postprocessing"
-
-    def sharpen(self, image: torch.Tensor, sharpen_radius: int, sigma:float, alpha: float):
+    def execute(cls, image: torch.Tensor, sharpen_radius: int, sigma:float, alpha: float) -> io.NodeOutput:
         if sharpen_radius == 0:
-            return (image,)
+            return io.NodeOutput(image)
 
         batch_size, height, width, channels = image.shape
         image = image.to(comfy.model_management.get_torch_device())
@@ -245,23 +206,29 @@ class Sharpen:
 
         result = torch.clamp(sharpened, 0, 1)
 
-        return (result.to(comfy.model_management.intermediate_device()),)
+        return io.NodeOutput(result.to(comfy.model_management.intermediate_device()))
 
-class ImageScaleToTotalPixels:
+class ImageScaleToTotalPixels(io.ComfyNode):
     upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
     crop_methods = ["disabled", "center"]
 
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
-                              "megapixels": ("FLOAT", {"default": 1.0, "min": 0.01, "max": 16.0, "step": 0.01}),
-                            }}
-    RETURN_TYPES = ("IMAGE",)
-    FUNCTION = "upscale"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageScaleToTotalPixels",
+            category="image/upscaling",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("upscale_method", options=cls.upscale_methods),
+                io.Float.Input("megapixels", default=1.0, min=0.01, max=16.0, step=0.01),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
-    CATEGORY = "image/upscaling"
-
-    def upscale(self, image, upscale_method, megapixels):
+    @classmethod
+    def execute(cls, image, upscale_method, megapixels) -> io.NodeOutput:
         samples = image.movedim(-1,1)
         total = int(megapixels * 1024 * 1024)
 
@@ -271,12 +238,18 @@ class ImageScaleToTotalPixels:
 
         s = comfy.utils.common_upscale(samples, width, height, upscale_method, "disabled")
         s = s.movedim(1,-1)
-        return (s,)
+        return io.NodeOutput(s)
 
-NODE_CLASS_MAPPINGS = {
-    "ImageBlend": Blend,
-    "ImageBlur": Blur,
-    "ImageQuantize": Quantize,
-    "ImageSharpen": Sharpen,
-    "ImageScaleToTotalPixels": ImageScaleToTotalPixels,
-}
+class PostProcessingExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            Blend,
+            Blur,
+            Quantize,
+            Sharpen,
+            ImageScaleToTotalPixels,
+        ]
+
+async def comfy_entrypoint() -> PostProcessingExtension:
+    return PostProcessingExtension()

comfy_extras/nodes_qwen.py

@@ -1,24 +1,29 @@
 import node_helpers
 import comfy.utils
 import math
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 
-class TextEncodeQwenImageEdit:
+class TextEncodeQwenImageEdit(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "clip": ("CLIP", ),
-            "prompt": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            },
-            "optional": {"vae": ("VAE", ),
-                         "image": ("IMAGE", ),}}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TextEncodeQwenImageEdit",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("prompt", multiline=True, dynamic_prompts=True),
+                io.Vae.Input("vae", optional=True),
+                io.Image.Input("image", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
-
-    CATEGORY = "advanced/conditioning"
-
-    def encode(self, clip, prompt, vae=None, image=None):
+    @classmethod
+    def execute(cls, clip, prompt, vae=None, image=None) -> io.NodeOutput:
         ref_latent = None
         if image is None:
             images = []
@@ -40,28 +45,30 @@ class TextEncodeQwenImageEdit:
         conditioning = clip.encode_from_tokens_scheduled(tokens)
         if ref_latent is not None:
             conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_latents": [ref_latent]}, append=True)
-        return (conditioning, )
+        return io.NodeOutput(conditioning)
 
 
-class TextEncodeQwenImageEditPlus:
+class TextEncodeQwenImageEditPlus(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "clip": ("CLIP", ),
-            "prompt": ("STRING", {"multiline": True, "dynamicPrompts": True}),
-            },
-            "optional": {"vae": ("VAE", ),
-                         "image1": ("IMAGE", ),
-                         "image2": ("IMAGE", ),
-                         "image3": ("IMAGE", ),
-                         }}
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TextEncodeQwenImageEditPlus",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("prompt", multiline=True, dynamic_prompts=True),
+                io.Vae.Input("vae", optional=True),
+                io.Image.Input("image1", optional=True),
+                io.Image.Input("image2", optional=True),
+                io.Image.Input("image3", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
-
-    CATEGORY = "advanced/conditioning"
-
-    def encode(self, clip, prompt, vae=None, image1=None, image2=None, image3=None):
+    @classmethod
+    def execute(cls, clip, prompt, vae=None, image1=None, image2=None, image3=None) -> io.NodeOutput:
         ref_latents = []
         images = [image1, image2, image3]
         images_vl = []
@@ -94,10 +101,17 @@ class TextEncodeQwenImageEditPlus:
         conditioning = clip.encode_from_tokens_scheduled(tokens)
         if len(ref_latents) > 0:
             conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_latents": ref_latents}, append=True)
-        return (conditioning, )
+        return io.NodeOutput(conditioning)
 
 
-NODE_CLASS_MAPPINGS = {
-    "TextEncodeQwenImageEdit": TextEncodeQwenImageEdit,
-    "TextEncodeQwenImageEditPlus": TextEncodeQwenImageEditPlus,
-}
+class QwenExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            TextEncodeQwenImageEdit,
+            TextEncodeQwenImageEditPlus,
+        ]
+
+
+async def comfy_entrypoint() -> QwenExtension:
+    return QwenExtension()

comfy_extras/nodes_rebatch.py

@@ -1,18 +1,25 @@
+from typing_extensions import override
 import torch
 
-class LatentRebatch:
+from comfy_api.latest import ComfyExtension, io
+
+
+class LatentRebatch(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "latents": ("LATENT",),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              }}
-    RETURN_TYPES = ("LATENT",)
-    INPUT_IS_LIST = True
-    OUTPUT_IS_LIST = (True, )
-
-    FUNCTION = "rebatch"
-
-    CATEGORY = "latent/batch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RebatchLatents",
+            display_name="Rebatch Latents",
+            category="latent/batch",
+            is_input_list=True,
+            inputs=[
+                io.Latent.Input("latents"),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(is_output_list=True),
+            ],
+        )
 
     @staticmethod
     def get_batch(latents, list_ind, offset):
@@ -53,7 +60,8 @@ class LatentRebatch:
         result = [torch.cat((b1, b2)) if torch.is_tensor(b1) else b1 + b2 for b1, b2 in zip(batch1, batch2)]
         return result
 
-    def rebatch(self, latents, batch_size):
+    @classmethod
+    def execute(cls, latents, batch_size):
         batch_size = batch_size[0]
 
         output_list = []
@@ -63,24 +71,24 @@ class LatentRebatch:
         for i in range(len(latents)):
             # fetch new entry of list
             #samples, masks, indices = self.get_batch(latents, i)
-            next_batch = self.get_batch(latents, i, processed)
+            next_batch = cls.get_batch(latents, i, processed)
             processed += len(next_batch[2])
             # set to current if current is None
             if current_batch[0] is None:
                 current_batch = next_batch
             # add previous to list if dimensions do not match
             elif next_batch[0].shape[-1] != current_batch[0].shape[-1] or next_batch[0].shape[-2] != current_batch[0].shape[-2]:
-                sliced, _ = self.slice_batch(current_batch, 1, batch_size)
+                sliced, _ = cls.slice_batch(current_batch, 1, batch_size)
                 output_list.append({'samples': sliced[0][0], 'noise_mask': sliced[1][0], 'batch_index': sliced[2][0]})
                 current_batch = next_batch
             # cat if everything checks out
             else:
-                current_batch = self.cat_batch(current_batch, next_batch)
+                current_batch = cls.cat_batch(current_batch, next_batch)
 
             # add to list if dimensions gone above target batch size
             if current_batch[0].shape[0] > batch_size:
                 num = current_batch[0].shape[0] // batch_size
-                sliced, remainder = self.slice_batch(current_batch, num, batch_size)
+                sliced, remainder = cls.slice_batch(current_batch, num, batch_size)
 
                 for i in range(num):
                     output_list.append({'samples': sliced[0][i], 'noise_mask': sliced[1][i], 'batch_index': sliced[2][i]})
@@ -89,7 +97,7 @@ class LatentRebatch:
 
         #add remainder
         if current_batch[0] is not None:
-            sliced, _ = self.slice_batch(current_batch, 1, batch_size)
+            sliced, _ = cls.slice_batch(current_batch, 1, batch_size)
             output_list.append({'samples': sliced[0][0], 'noise_mask': sliced[1][0], 'batch_index': sliced[2][0]})
 
         #get rid of empty masks
@@ -97,23 +105,27 @@ class LatentRebatch:
             if s['noise_mask'].mean() == 1.0:
                 del s['noise_mask']
 
-        return (output_list,)
+        return io.NodeOutput(output_list)
 
-class ImageRebatch:
+class ImageRebatch(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "images": ("IMAGE",),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              }}
-    RETURN_TYPES = ("IMAGE",)
-    INPUT_IS_LIST = True
-    OUTPUT_IS_LIST = (True, )
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RebatchImages",
+            display_name="Rebatch Images",
+            category="image/batch",
+            is_input_list=True,
+            inputs=[
+                io.Image.Input("images"),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Image.Output(is_output_list=True),
+            ],
+        )
 
-    FUNCTION = "rebatch"
-
-    CATEGORY = "image/batch"
-
-    def rebatch(self, images, batch_size):
+    @classmethod
+    def execute(cls, images, batch_size):
         batch_size = batch_size[0]
 
         output_list = []
@@ -125,14 +137,17 @@ class ImageRebatch:
         for i in range(0, len(all_images), batch_size):
             output_list.append(torch.cat(all_images[i:i+batch_size], dim=0))
 
-        return (output_list,)
+        return io.NodeOutput(output_list)
 
-NODE_CLASS_MAPPINGS = {
-    "RebatchLatents": LatentRebatch,
-    "RebatchImages": ImageRebatch,
-}
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "RebatchLatents": "Rebatch Latents",
-    "RebatchImages": "Rebatch Images",
-}
+class RebatchExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            LatentRebatch,
+            ImageRebatch,
+        ]
+
+
+async def comfy_entrypoint() -> RebatchExtension:
+    return RebatchExtension()

comfy_extras/nodes_sag.py

@@ -2,10 +2,13 @@ import torch
 from torch import einsum
 import torch.nn.functional as F
 import math
+from typing_extensions import override
 
 from einops import rearrange, repeat
 from comfy.ldm.modules.attention import optimized_attention
 import comfy.samplers
+from comfy_api.latest import ComfyExtension, io
+
 
 # from comfy/ldm/modules/attention.py
 # but modified to return attention scores as well as output
@@ -104,19 +107,26 @@ def gaussian_blur_2d(img, kernel_size, sigma):
     img = F.conv2d(img, kernel2d, groups=img.shape[-3])
     return img
 
-class SelfAttentionGuidance:
+class SelfAttentionGuidance(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                             "scale": ("FLOAT", {"default": 0.5, "min": -2.0, "max": 5.0, "step": 0.01}),
-                             "blur_sigma": ("FLOAT", {"default": 2.0, "min": 0.0, "max": 10.0, "step": 0.1}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SelfAttentionGuidance",
+            display_name="Self-Attention Guidance",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale", default=0.5, min=-2.0, max=5.0, step=0.01),
+                io.Float.Input("blur_sigma", default=2.0, min=0.0, max=10.0, step=0.1),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
 
-    CATEGORY = "_for_testing"
-
-    def patch(self, model, scale, blur_sigma):
+    @classmethod
+    def execute(cls, model, scale, blur_sigma):
         m = model.clone()
 
         attn_scores = None
@@ -170,12 +180,16 @@ class SelfAttentionGuidance:
         # unet.mid_block.attentions[0].transformer_blocks[0].attn1.patch
         m.set_model_attn1_replace(attn_and_record, "middle", 0, 0)
 
-        return (m, )
+        return io.NodeOutput(m)
 
-NODE_CLASS_MAPPINGS = {
-    "SelfAttentionGuidance": SelfAttentionGuidance,
-}
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "SelfAttentionGuidance": "Self-Attention Guidance",
-}
+class SagExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            SelfAttentionGuidance,
+        ]
+
+
+async def comfy_entrypoint() -> SagExtension:
+    return SagExtension()

comfy_extras/nodes_sdupscale.py

@@ -1,23 +1,31 @@
+from typing_extensions import override
+
 import torch
 import comfy.utils
+from comfy_api.latest import ComfyExtension, io
 
-class SD_4XUpscale_Conditioning:
+class SD_4XUpscale_Conditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "images": ("IMAGE",),
-                              "positive": ("CONDITIONING",),
-                              "negative": ("CONDITIONING",),
-                              "scale_ratio": ("FLOAT", {"default": 4.0, "min": 0.0, "max": 10.0, "step": 0.01}),
-                              "noise_augmentation": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),
-                             }}
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SD_4XUpscale_Conditioning",
+            category="conditioning/upscale_diffusion",
+            inputs=[
+                io.Image.Input("images"),
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Float.Input("scale_ratio", default=4.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("noise_augmentation", default=0.0, min=0.0, max=1.0, step=0.001),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
 
-    FUNCTION = "encode"
-
-    CATEGORY = "conditioning/upscale_diffusion"
-
-    def encode(self, images, positive, negative, scale_ratio, noise_augmentation):
+    @classmethod
+    def execute(cls, images, positive, negative, scale_ratio, noise_augmentation):
         width = max(1, round(images.shape[-2] * scale_ratio))
         height = max(1, round(images.shape[-3] * scale_ratio))
 
@@ -39,8 +47,16 @@ class SD_4XUpscale_Conditioning:
             out_cn.append(n)
 
         latent = torch.zeros([images.shape[0], 4, height // 4, width // 4])
-        return (out_cp, out_cn, {"samples":latent})
+        return io.NodeOutput(out_cp, out_cn, {"samples":latent})
 
-NODE_CLASS_MAPPINGS = {
-    "SD_4XUpscale_Conditioning": SD_4XUpscale_Conditioning,
-}
+
+class SdUpscaleExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            SD_4XUpscale_Conditioning,
+        ]
+
+
+async def comfy_entrypoint() -> SdUpscaleExtension:
+    return SdUpscaleExtension()

comfy_extras/nodes_stable3d.py

@@ -1,6 +1,8 @@
 import torch
 import nodes
 import comfy.utils
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 
 def camera_embeddings(elevation, azimuth):
     elevation = torch.as_tensor([elevation])
@@ -20,26 +22,31 @@ def camera_embeddings(elevation, azimuth):
     return embeddings
 
 
-class StableZero123_Conditioning:
+class StableZero123_Conditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "clip_vision": ("CLIP_VISION",),
-                              "init_image": ("IMAGE",),
-                              "vae": ("VAE",),
-                              "width": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "height": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              "elevation": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                              "azimuth": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                             }}
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableZero123_Conditioning",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
 
-    FUNCTION = "encode"
-
-    CATEGORY = "conditioning/3d_models"
-
-    def encode(self, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth):
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth) -> io.NodeOutput:
         output = clip_vision.encode_image(init_image)
         pooled = output.image_embeds.unsqueeze(0)
         pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@@ -51,30 +58,35 @@ class StableZero123_Conditioning:
         positive = [[cond, {"concat_latent_image": t}]]
         negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
         latent = torch.zeros([batch_size, 4, height // 8, width // 8])
-        return (positive, negative, {"samples":latent})
+        return io.NodeOutput(positive, negative, {"samples":latent})
 
-class StableZero123_Conditioning_Batched:
+class StableZero123_Conditioning_Batched(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "clip_vision": ("CLIP_VISION",),
-                              "init_image": ("IMAGE",),
-                              "vae": ("VAE",),
-                              "width": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "height": ("INT", {"default": 256, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
-                              "elevation": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                              "azimuth": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                              "elevation_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                              "azimuth_batch_increment": ("FLOAT", {"default": 0.0, "min": -180.0, "max": 180.0, "step": 0.1, "round": False}),
-                             }}
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableZero123_Conditioning_Batched",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("elevation_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
 
-    FUNCTION = "encode"
-
-    CATEGORY = "conditioning/3d_models"
-
-    def encode(self, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment):
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment) -> io.NodeOutput:
         output = clip_vision.encode_image(init_image)
         pooled = output.image_embeds.unsqueeze(0)
         pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@@ -93,27 +105,32 @@ class StableZero123_Conditioning_Batched:
         positive = [[cond, {"concat_latent_image": t}]]
         negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
         latent = torch.zeros([batch_size, 4, height // 8, width // 8])
-        return (positive, negative, {"samples":latent, "batch_index": [0] * batch_size})
+        return io.NodeOutput(positive, negative, {"samples":latent, "batch_index": [0] * batch_size})
 
-class SV3D_Conditioning:
+class SV3D_Conditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "clip_vision": ("CLIP_VISION",),
-                              "init_image": ("IMAGE",),
-                              "vae": ("VAE",),
-                              "width": ("INT", {"default": 576, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "height": ("INT", {"default": 576, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 8}),
-                              "video_frames": ("INT", {"default": 21, "min": 1, "max": 4096}),
-                              "elevation": ("FLOAT", {"default": 0.0, "min": -90.0, "max": 90.0, "step": 0.1, "round": False}),
-                             }}
-    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
-    RETURN_NAMES = ("positive", "negative", "latent")
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SV3D_Conditioning",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("video_frames", default=21, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-90.0, max=90.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
 
-    FUNCTION = "encode"
-
-    CATEGORY = "conditioning/3d_models"
-
-    def encode(self, clip_vision, init_image, vae, width, height, video_frames, elevation):
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, video_frames, elevation) -> io.NodeOutput:
         output = clip_vision.encode_image(init_image)
         pooled = output.image_embeds.unsqueeze(0)
         pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
@@ -133,11 +150,17 @@ class SV3D_Conditioning:
         positive = [[pooled, {"concat_latent_image": t, "elevation": elevations, "azimuth": azimuths}]]
         negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t), "elevation": elevations, "azimuth": azimuths}]]
         latent = torch.zeros([video_frames, 4, height // 8, width // 8])
-        return (positive, negative, {"samples":latent})
+        return io.NodeOutput(positive, negative, {"samples":latent})
 
 
-NODE_CLASS_MAPPINGS = {
-    "StableZero123_Conditioning": StableZero123_Conditioning,
-    "StableZero123_Conditioning_Batched": StableZero123_Conditioning_Batched,
-    "SV3D_Conditioning": SV3D_Conditioning,
-}
+class Stable3DExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            StableZero123_Conditioning,
+            StableZero123_Conditioning_Batched,
+            SV3D_Conditioning,
+        ]
+
+async def comfy_entrypoint() -> Stable3DExtension:
+    return Stable3DExtension()

comfy_extras/nodes_tcfg.py

@@ -1,8 +1,9 @@
 # TCFG: Tangential Damping Classifier-free Guidance - (arXiv: https://arxiv.org/abs/2503.18137)
 
+from typing_extensions import override
 import torch
 
-from comfy.comfy_types import IO, ComfyNodeABC, InputTypeDict
+from comfy_api.latest import ComfyExtension, io
 
 
 def score_tangential_damping(cond_score: torch.Tensor, uncond_score: torch.Tensor) -> torch.Tensor:
@@ -26,23 +27,24 @@ def score_tangential_damping(cond_score: torch.Tensor, uncond_score: torch.Tenso
     return uncond_score_td.reshape_as(uncond_score).to(uncond_score.dtype)
 
 
-class TCFG(ComfyNodeABC):
+class TCFG(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(cls) -> InputTypeDict:
-        return {
-            "required": {
-                "model": (IO.MODEL, {}),
-            }
-        }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TCFG",
+            display_name="Tangential Damping CFG",
+            category="advanced/guidance",
+            description="TCFG – Tangential Damping CFG (2503.18137)\n\nRefine the uncond (negative) to align with the cond (positive) for improving quality.",
+            inputs=[
+                io.Model.Input("model"),
+            ],
+            outputs=[
+                io.Model.Output(display_name="patched_model"),
+            ],
+        )
 
-    RETURN_TYPES = (IO.MODEL,)
-    RETURN_NAMES = ("patched_model",)
-    FUNCTION = "patch"
-
-    CATEGORY = "advanced/guidance"
-    DESCRIPTION = "TCFG – Tangential Damping CFG (2503.18137)\n\nRefine the uncond (negative) to align with the cond (positive) for improving quality."
-
-    def patch(self, model):
+    @classmethod
+    def execute(cls, model):
         m = model.clone()
 
         def tangential_damping_cfg(args):
@@ -59,13 +61,16 @@ class TCFG(ComfyNodeABC):
             return [cond_pred, uncond_pred_td] + conds_out[2:]
 
         m.set_model_sampler_pre_cfg_function(tangential_damping_cfg)
-        return (m,)
+        return io.NodeOutput(m)
 
 
-NODE_CLASS_MAPPINGS = {
-    "TCFG": TCFG,
-}
+class TcfgExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            TCFG,
+        ]
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "TCFG": "Tangential Damping CFG",
-}
+
+async def comfy_entrypoint() -> TcfgExtension:
+    return TcfgExtension()

comfy_extras/nodes_tomesd.py

@@ -1,7 +1,9 @@
 #Taken from: https://github.com/dbolya/tomesd
 
 import torch
-from typing import Tuple, Callable
+from typing import Tuple, Callable, Optional
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 import math
 
 def do_nothing(x: torch.Tensor, mode:str=None):
@@ -144,33 +146,45 @@ def get_functions(x, ratio, original_shape):
 
 
 
-class TomePatchModel:
+class TomePatchModel(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                              "ratio": ("FLOAT", {"default": 0.3, "min": 0.0, "max": 1.0, "step": 0.01}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TomePatchModel",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("ratio", default=0.3, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[io.Model.Output()],
+        )
 
-    CATEGORY = "model_patches/unet"
-
-    def patch(self, model, ratio):
-        self.u = None
+    @classmethod
+    def execute(cls, model, ratio) -> io.NodeOutput:
+        u: Optional[Callable] = None
         def tomesd_m(q, k, v, extra_options):
+            nonlocal u
             #NOTE: In the reference code get_functions takes x (input of the transformer block) as the argument instead of q
             #however from my basic testing it seems that using q instead gives better results
-            m, self.u = get_functions(q, ratio, extra_options["original_shape"])
+            m, u = get_functions(q, ratio, extra_options["original_shape"])
             return m(q), k, v
         def tomesd_u(n, extra_options):
-            return self.u(n)
+            nonlocal u
+            return u(n)
 
         m = model.clone()
         m.set_model_attn1_patch(tomesd_m)
         m.set_model_attn1_output_patch(tomesd_u)
-        return (m, )
+        return io.NodeOutput(m)
 
 
-NODE_CLASS_MAPPINGS = {
-    "TomePatchModel": TomePatchModel,
-}
+class TomePatchModelExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            TomePatchModel,
+        ]
+
+
+async def comfy_entrypoint() -> TomePatchModelExtension:
+    return TomePatchModelExtension()

comfy_extras/nodes_torch_compile.py

@@ -1,23 +1,39 @@
+from typing_extensions import override
+from comfy_api.latest import ComfyExtension, io
 from comfy_api.torch_helpers import set_torch_compile_wrapper
 
 
-class TorchCompileModel:
+class TorchCompileModel(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                             "backend": (["inductor", "cudagraphs"],),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="TorchCompileModel",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input(
+                    "backend",
+                    options=["inductor", "cudagraphs"],
+                ),
+            ],
+            outputs=[io.Model.Output()],
+            is_experimental=True,
+        )
 
-    CATEGORY = "_for_testing"
-    EXPERIMENTAL = True
-
-    def patch(self, model, backend):
+    @classmethod
+    def execute(cls, model, backend) -> io.NodeOutput:
         m = model.clone()
         set_torch_compile_wrapper(model=m, backend=backend)
-        return (m, )
+        return io.NodeOutput(m)
 
-NODE_CLASS_MAPPINGS = {
-    "TorchCompileModel": TorchCompileModel,
-}
+
+class TorchCompileExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            TorchCompileModel,
+        ]
+
+
+async def comfy_entrypoint() -> TorchCompileExtension:
+    return TorchCompileExtension()

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.3.60"
+__version__ = "0.3.63"

custom_nodes/example_node.py.example

@@ -1,96 +1,70 @@
-class Example:
+from typing_extensions import override
+
+from comfy_api.latest import ComfyExtension, io
+
+
+class Example(io.ComfyNode):
     """
-    A example node
+    An example node
 
     Class methods
     -------------
-    INPUT_TYPES (dict):
-        Tell the main program input parameters of nodes.
-    IS_CHANGED:
+    define_schema (io.Schema):
+        Tell the main program the metadata, input, output parameters of nodes.
+    fingerprint_inputs:
         optional method to control when the node is re executed.
+    check_lazy_status:
+        optional method to control list of input names that need to be evaluated.
 
-    Attributes
-    ----------
-    RETURN_TYPES (`tuple`):
-        The type of each element in the output tuple.
-    RETURN_NAMES (`tuple`):
-        Optional: The name of each output in the output tuple.
-    FUNCTION (`str`):
-        The name of the entry-point method. For example, if `FUNCTION = "execute"` then it will run Example().execute()
-    OUTPUT_NODE ([`bool`]):
-        If this node is an output node that outputs a result/image from the graph. The SaveImage node is an example.
-        The backend iterates on these output nodes and tries to execute all their parents if their parent graph is properly connected.
-        Assumed to be False if not present.
-    CATEGORY (`str`):
-        The category the node should appear in the UI.
-    DEPRECATED (`bool`):
-        Indicates whether the node is deprecated. Deprecated nodes are hidden by default in the UI, but remain
-        functional in existing workflows that use them.
-    EXPERIMENTAL (`bool`):
-        Indicates whether the node is experimental. Experimental nodes are marked as such in the UI and may be subject to
-        significant changes or removal in future versions. Use with caution in production workflows.
-    execute(s) -> tuple || None:
-        The entry point method. The name of this method must be the same as the value of property `FUNCTION`.
-        For example, if `FUNCTION = "execute"` then this method's name must be `execute`, if `FUNCTION = "foo"` then it must be `foo`.
     """
-    def __init__(self):
-        pass
 
     @classmethod
-    def INPUT_TYPES(s):
+    def define_schema(cls) -> io.Schema:
         """
-            Return a dictionary which contains config for all input fields.
-            Some types (string): "MODEL", "VAE", "CLIP", "CONDITIONING", "LATENT", "IMAGE", "INT", "STRING", "FLOAT".
-            Input types "INT", "STRING" or "FLOAT" are special values for fields on the node.
-            The type can be a list for selection.
-
-            Returns: `dict`:
-                - Key input_fields_group (`string`): Can be either required, hidden or optional. A node class must have property `required`
-                - Value input_fields (`dict`): Contains input fields config:
-                    * Key field_name (`string`): Name of a entry-point method's argument
-                    * Value field_config (`tuple`):
-                        + First value is a string indicate the type of field or a list for selection.
-                        + Second value is a config for type "INT", "STRING" or "FLOAT".
+            Return a schema which contains all information about the node.
+            Some types: "Model", "Vae", "Clip", "Conditioning", "Latent", "Image", "Int", "String", "Float", "Combo".
+            For outputs the "io.Model.Output" should be used, for inputs the "io.Model.Input" can be used.
+            The type can be a "Combo" - this will be a list for selection.
         """
-        return {
-            "required": {
-                "image": ("IMAGE",),
-                "int_field": ("INT", {
-                    "default": 0, 
-                    "min": 0, #Minimum value
-                    "max": 4096, #Maximum value
-                    "step": 64, #Slider's step
-                    "display": "number", # Cosmetic only: display as "number" or "slider"
-                    "lazy": True # Will only be evaluated if check_lazy_status requires it
-                }),
-                "float_field": ("FLOAT", {
-                    "default": 1.0,
-                    "min": 0.0,
-                    "max": 10.0,
-                    "step": 0.01,
-                    "round": 0.001, #The value representing the precision to round to, will be set to the step value by default. Can be set to False to disable rounding.
-                    "display": "number",
-                    "lazy": True
-                }),
-                "print_to_screen": (["enable", "disable"],),
-                "string_field": ("STRING", {
-                    "multiline": False, #True if you want the field to look like the one on the ClipTextEncode node
-                    "default": "Hello World!",
-                    "lazy": True
-                }),
-            },
-        }
+        return io.Schema(
+            node_id="Example",
+            display_name="Example Node",
+            category="Example",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input(
+                    "int_field",
+                    min=0,
+                    max=4096,
+                    step=64, # Slider's step
+                    display_mode=io.NumberDisplay.number,  # Cosmetic only: display as "number" or "slider"
+                    lazy=True,  # Will only be evaluated if check_lazy_status requires it
+                ),
+                io.Float.Input(
+                    "float_field",
+                    default=1.0,
+                    min=0.0,
+                    max=10.0,
+                    step=0.01,
+                    round=0.001, #The value representing the precision to round to, will be set to the step value by default. Can be set to False to disable rounding.
+                    display_mode=io.NumberDisplay.number,
+                    lazy=True,
+                ),
+                io.Combo.Input("print_to_screen", options=["enable", "disable"]),
+                io.String.Input(
+                    "string_field",
+                    multiline=False,  # True if you want the field to look like the one on the ClipTextEncode node
+                    default="Hello world!",
+                    lazy=True,
+                )
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
 
-    RETURN_TYPES = ("IMAGE",)
-    #RETURN_NAMES = ("image_output_name",)
-
-    FUNCTION = "test"
-
-    #OUTPUT_NODE = False
-
-    CATEGORY = "Example"
-
-    def check_lazy_status(self, image, string_field, int_field, float_field, print_to_screen):
+    @classmethod
+    def check_lazy_status(cls, image, string_field, int_field, float_field, print_to_screen):
         """
             Return a list of input names that need to be evaluated.
 
@@ -107,7 +81,8 @@ class Example:
         else:
             return []
 
-    def test(self, image, string_field, int_field, float_field, print_to_screen):
+    @classmethod
+    def execute(cls, image, string_field, int_field, float_field, print_to_screen) -> io.NodeOutput:
         if print_to_screen == "enable":
             print(f"""Your input contains:
                 string_field aka input text: {string_field}
@@ -116,7 +91,7 @@ class Example:
             """)
         #do some processing on the image, in this example I just invert it
         image = 1.0 - image
-        return (image,)
+        return io.NodeOutput(image)
 
     """
         The node will always be re executed if any of the inputs change but
@@ -127,7 +102,7 @@ class Example:
         changes between executions the LoadImage node is executed again.
     """
     #@classmethod
-    #def IS_CHANGED(s, image, string_field, int_field, float_field, print_to_screen):
+    #def fingerprint_inputs(s, image, string_field, int_field, float_field, print_to_screen):
     #    return ""
 
 # Set the web directory, any .js file in that directory will be loaded by the frontend as a frontend extension
@@ -143,13 +118,13 @@ async def get_hello(request):
     return web.json_response("hello")
 
 
-# A dictionary that contains all nodes you want to export with their names
-# NOTE: names should be globally unique
-NODE_CLASS_MAPPINGS = {
-    "Example": Example
-}
+class ExampleExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            Example,
+        ]
 
-# A dictionary that contains the friendly/humanly readable titles for the nodes
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "Example": "Example Node"
-}
+
+async def comfy_entrypoint() -> ExampleExtension:  # ComfyUI calls this to load your extension and its nodes.
+    return ExampleExtension()

main.py

@@ -115,6 +115,7 @@ if os.name == "nt":
     os.environ['MIMALLOC_PURGE_DELAY'] = '0'
 
 if __name__ == "__main__":
+    os.environ['TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL'] = '1'
     if args.default_device is not None:
         default_dev = args.default_device
         devices = list(range(32))
@@ -127,6 +128,7 @@ if __name__ == "__main__":
     if args.cuda_device is not None:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(args.cuda_device)
         os.environ['HIP_VISIBLE_DEVICES'] = str(args.cuda_device)
+        os.environ["ASCEND_RT_VISIBLE_DEVICES"] = str(args.cuda_device)
         logging.info("Set cuda device to: {}".format(args.cuda_device))
 
     if args.oneapi_device_selector is not None:

middleware/cache_middleware.py

@@ -26,11 +26,12 @@ async def cache_control(
     """Cache control middleware that sets appropriate cache headers based on file type and response status"""
     response: web.Response = await handler(request)
 
-    if (
-        request.path.endswith(".js")
-        or request.path.endswith(".css")
-        or request.path.endswith("index.json")
-    ):
+    path_filename = request.path.rsplit("/", 1)[-1]
+    is_entry_point = path_filename.startswith("index") and path_filename.endswith(
+        ".json"
+    )
+
+    if request.path.endswith(".js") or request.path.endswith(".css") or is_entry_point:
         response.headers.setdefault("Cache-Control", "no-cache")
         return response
 

nodes.py

@@ -2297,6 +2297,7 @@ async def init_builtin_extra_nodes():
         "nodes_gits.py",
         "nodes_controlnet.py",
         "nodes_hunyuan.py",
+        "nodes_eps.py",
         "nodes_flux.py",
         "nodes_lora_extract.py",
         "nodes_torch_compile.py",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.3.60"
+version = "0.3.63"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"
@@ -22,3 +22,53 @@ lint.select = [
   "F",
 ]
 exclude = ["*.ipynb", "**/generated/*.pyi"]
+
+[tool.pylint]
+master.py-version = "3.9"
+master.extension-pkg-allow-list = [
+  "pydantic",
+]
+reports.output-format = "colorized"
+similarities.ignore-imports = "yes"
+messages_control.disable = [
+  "missing-module-docstring",
+  "missing-class-docstring",
+  "missing-function-docstring",
+  "line-too-long",
+  "too-few-public-methods",
+  "too-many-public-methods",
+  "too-many-instance-attributes",
+  "too-many-positional-arguments",
+  "broad-exception-raised",
+  "too-many-lines",
+  "invalid-name",
+  "unused-argument",
+  "broad-exception-caught",
+  "consider-using-with",
+  "fixme",
+  "too-many-statements",
+  "too-many-branches",
+  "too-many-locals",
+  "too-many-arguments",
+  "duplicate-code",
+  "abstract-method",
+  "superfluous-parens",
+  "arguments-differ",
+  "redefined-builtin",
+  "unnecessary-lambda",
+  "dangerous-default-value",
+  # next warnings should be fixed in future
+  "bad-classmethod-argument",  # Class method should have 'cls' as first argument
+  "wrong-import-order",  # Standard imports should be placed before third party imports
+  "logging-fstring-interpolation", # Use lazy % formatting in logging functions
+  "ungrouped-imports",
+  "unnecessary-pass",
+  "unidiomatic-typecheck",
+  "unnecessary-lambda-assignment",
+  "no-else-return",
+  "no-else-raise",
+  "invalid-overridden-method",
+  "unused-variable",
+  "pointless-string-statement",
+  "redefined-outer-name",
+]

requirements.txt

@@ -1,5 +1,5 @@
-comfyui-frontend-package==1.26.13
-comfyui-workflow-templates==0.1.86
+comfyui-frontend-package==1.27.7
+comfyui-workflow-templates==0.1.93
 comfyui-embedded-docs==0.2.6
 torch
 torchsde
@@ -25,6 +25,5 @@ av>=14.2.0
 #non essential dependencies:
 kornia>=0.7.1
 spandrel
-soundfile
 pydantic~=2.0
 pydantic-settings~=2.0

server.py

@@ -550,6 +550,8 @@ class PromptServer():
             vram_total, torch_vram_total = comfy.model_management.get_total_memory(device, torch_total_too=True)
             vram_free, torch_vram_free = comfy.model_management.get_free_memory(device, torch_free_too=True)
             required_frontend_version = FrontendManager.get_required_frontend_version()
+            installed_templates_version = FrontendManager.get_installed_templates_version()
+            required_templates_version = FrontendManager.get_required_templates_version()
 
             system_stats = {
                 "system": {
@@ -558,6 +560,8 @@ class PromptServer():
                     "ram_free": ram_free,
                     "comfyui_version": __version__,
                     "required_frontend_version": required_frontend_version,
+                    "installed_templates_version": installed_templates_version,
+                    "required_templates_version": required_templates_version,
                     "python_version": sys.version,
                     "pytorch_version": comfy.model_management.torch_version,
                     "embedded_python": os.path.split(os.path.split(sys.executable)[0])[1] == "python_embeded",

tests-unit/app_test/frontend_manager_test.py

@@ -205,3 +205,74 @@ numpy"""
 
     # Assert
     assert version is None
+
+
+def test_get_templates_version():
+    # Arrange
+    expected_version = "0.1.41"
+    mock_requirements_content = """torch
+torchsde
+comfyui-frontend-package==1.25.0
+comfyui-workflow-templates==0.1.41
+other-package==1.0.0
+numpy"""
+
+    # Act
+    with patch("builtins.open", mock_open(read_data=mock_requirements_content)):
+        version = FrontendManager.get_required_templates_version()
+
+    # Assert
+    assert version == expected_version
+
+
+def test_get_templates_version_not_found():
+    # Arrange
+    mock_requirements_content = """torch
+torchsde
+comfyui-frontend-package==1.25.0
+other-package==1.0.0
+numpy"""
+
+    # Act
+    with patch("builtins.open", mock_open(read_data=mock_requirements_content)):
+        version = FrontendManager.get_required_templates_version()
+
+    # Assert
+    assert version is None
+
+
+def test_get_templates_version_invalid_semver():
+    # Arrange
+    mock_requirements_content = """torch
+torchsde
+comfyui-workflow-templates==1.0.0.beta
+other-package==1.0.0
+numpy"""
+
+    # Act
+    with patch("builtins.open", mock_open(read_data=mock_requirements_content)):
+        version = FrontendManager.get_required_templates_version()
+
+    # Assert
+    assert version is None
+
+
+def test_get_installed_templates_version():
+    # Arrange
+    expected_version = "0.1.40"
+
+    # Act
+    with patch("app.frontend_management.version", return_value=expected_version):
+        version = FrontendManager.get_installed_templates_version()
+
+    # Assert
+    assert version == expected_version
+
+
+def test_get_installed_templates_version_not_installed():
+    # Act
+    with patch("app.frontend_management.version", side_effect=Exception("Package not found")):
+        version = FrontendManager.get_installed_templates_version()
+
+    # Assert
+    assert version is None

tests-unit/server_test/test_cache_control.py

@@ -48,6 +48,13 @@ CACHE_SCENARIOS = [
         "expected_cache": "no-cache",
         "should_have_header": True,
     },
+    {
+        "name": "localized_index_json_no_cache",
+        "path": "/templates/index.zh.json",
+        "status": 200,
+        "expected_cache": "no-cache",
+        "should_have_header": True,
+    },
     # Non-matching files
     {
         "name": "html_no_header",