ComfyUI v0.5.1

* Update release workflows for branch process

* Adjust branch order in workflow triggers

* Revert changes in test workflows

.ci/manager_windows/install_manager.bat

@@ -1,4 +0,0 @@
-@echo off
-..\python_embeded\python.exe .\install_manager.py ..\ComfyUI\
-echo Installed manager through pip package, if not already installed.
-pause

.ci/manager_windows/install_manager.py

@@ -1,24 +0,0 @@
-import sys
-import os
-
-repo_path = str(sys.argv[1])
-repo_manager_req_path = os.path.join(repo_path, "manager_requirements.txt")
-
-if os.path.exists(repo_manager_req_path):
-    import subprocess
-    # if not installed, we get 'WARNING: Package(s) not found: comfyui_manager'
-    # if installed, there will be a line like 'Version: 0.1.0' = False
-    try:
-        output = subprocess.check_output([sys.executable, '-s', '-m', 'pip', 'show', 'comfyui_manager'])
-        if 'Version:' in output.decode('utf-8'):
-            print("comfyui_manager is already installed, will attempt to update to matching version of ComfyUI.")  # noqa: T201
-        else:
-            print("comfyui_manager is not installed, will install it now.")  # noqa: T201
-    except:
-        pass
-
-    try:
-        subprocess.check_call([sys.executable, '-s', '-m', 'pip', 'install', '-r', repo_manager_req_path])
-        print("comfyui_manager installed successfully.")  # noqa: T201
-    except:
-        print("Failed to install comfyui_manager, please install it manually.")  # noqa: T201

.ci/update_windows/update.py

@@ -126,8 +126,6 @@ cur_path = os.path.dirname(update_py_path)
 req_path = os.path.join(cur_path, "current_requirements.txt")
 repo_req_path = os.path.join(repo_path, "requirements.txt")
 
-manager_req_path = os.path.join(cur_path, "current_manager_requirements.txt")
-repo_manager_req_path = os.path.join(repo_path, "manager_requirements.txt")
 
 def files_equal(file1, file2):
     try:
@@ -154,25 +152,6 @@ if not os.path.exists(req_path) or not files_equal(repo_req_path, req_path):
     except:
         pass
 
-if os.path.exists(repo_manager_req_path) and (not os.path.exists(manager_req_path) or not files_equal(repo_manager_req_path, manager_req_path)):
-    import subprocess
-    # first, confirm that comfyui_manager package is installed; only update it if it is
-    # if not installed, we get 'WARNING: Package(s) not found: comfyui_manager'
-    # if installed, there will be a line like 'Version: 0.1.0'
-    update_manager = False
-    try:
-        output = subprocess.check_output([sys.executable, '-s', '-m', 'pip', 'show', 'comfyui_manager'])
-        if 'Version:' in output.decode('utf-8'):
-            update_manager = True
-    except:
-        pass
-
-    if update_manager:
-        try:
-            subprocess.check_call([sys.executable, '-s', '-m', 'pip', 'install', '-r', repo_manager_req_path])
-            shutil.copy(repo_manager_req_path, manager_req_path)
-        except:
-            pass
 
 stable_update_script = os.path.join(repo_path, ".ci/update_windows/update_comfyui_stable.bat")
 stable_update_script_to = os.path.join(cur_path, "update_comfyui_stable.bat")

.ci/windows_amd_base_files/run_amd_gpu.bat

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

.ci/windows_amd_base_files/run_amd_gpu_disable_smart_memory.bat

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

.ci/windows_nightly_base_files/run_nvidia_gpu_fast.bat

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

.ci/windows_nvidia_base_files/advanced/run_nvidia_gpu_disable_api_nodes.bat

@@ -1,3 +1,3 @@
-..\python_embeded\python.exe -s ..\ComfyUI\main.py --windows-standalone-build --enable-manager --disable-api-nodes
+..\python_embeded\python.exe -s ..\ComfyUI\main.py --windows-standalone-build --disable-api-nodes
 echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest.
 pause

.ci/windows_nvidia_base_files/run_cpu.bat

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

.ci/windows_nvidia_base_files/run_nvidia_gpu.bat

@@ -1,3 +1,3 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --enable-manager
+.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
 echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest.
 pause

.ci/windows_nvidia_base_files/run_nvidia_gpu_fast_fp16_accumulation.bat

@@ -1,3 +1,3 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --enable-manager --fast fp16_accumulation
+.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast fp16_accumulation
 echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest.
 pause

.github/workflows/test-ci.yml

@@ -5,6 +5,7 @@ on:
   push:
     branches:
       - master
+      - release/**
     paths-ignore:
       - 'app/**'
       - 'input/**'

.github/workflows/test-execution.yml

@@ -2,9 +2,9 @@ name: Execution Tests
 
 on:
   push:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
   pull_request:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
 
 jobs:
   test:

.github/workflows/test-launch.yml

@@ -2,9 +2,9 @@ name: Test server launches without errors
 
 on:
   push:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
   pull_request:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
 
 jobs:
   test:

.github/workflows/test-unit.yml

@@ -2,9 +2,9 @@ name: Unit Tests
 
 on:
   push:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
   pull_request:
-    branches: [ main, master ]
+    branches: [ main, master, release/** ]
 
 jobs:
   test:

.github/workflows/update-version.yml

@@ -6,6 +6,7 @@ on:
       - "pyproject.toml"
     branches:
       - master
+      - release/**
 
 jobs:
   update-version:

comfy/k_diffusion/sampling.py

@@ -1618,6 +1618,17 @@ def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=Non
             x = x + sde_noise * sigmas[i + 1] * s_noise
     return x
 
+@torch.no_grad()
+def sample_exp_heun_2_x0(model, x, sigmas, extra_args=None, callback=None, disable=None, solver_type="phi_2"):
+    """Deterministic exponential Heun second order method in data prediction (x0) and logSNR time."""
+    return sample_seeds_2(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=0.0, s_noise=0.0, noise_sampler=None, r=1.0, solver_type=solver_type)
+
+
+@torch.no_grad()
+def sample_exp_heun_2_x0_sde(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, solver_type="phi_2"):
+    """Stochastic exponential Heun second order method in data prediction (x0) and logSNR time."""
+    return sample_seeds_2(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, r=1.0, solver_type=solver_type)
+
 
 @torch.no_grad()
 def sample_seeds_3(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r_1=1./3, r_2=2./3):
@@ -1765,7 +1776,7 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F
         # Predictor
         if sigmas[i + 1] == 0:
             # Denoising step
-            x = denoised
+            x_pred = denoised
         else:
             tau_t = tau_func(sigmas[i + 1])
             curr_lambdas = lambdas[i - predictor_order_used + 1:i + 1]
@@ -1786,7 +1797,7 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F
             if tau_t > 0 and s_noise > 0:
                 noise = noise_sampler(sigmas[i], sigmas[i + 1]) * sigmas[i + 1] * (-2 * tau_t ** 2 * h).expm1().neg().sqrt() * s_noise
                 x_pred = x_pred + noise
-    return x
+    return x_pred
 
 
 @torch.no_grad()

comfy/ldm/lumina/model.py

@@ -634,8 +634,11 @@ class NextDiT(nn.Module):
         img, mask, img_size, cap_size, freqs_cis = self.patchify_and_embed(x, cap_feats, cap_mask, adaln_input, num_tokens, transformer_options=transformer_options)
         freqs_cis = freqs_cis.to(img.device)
 
+        transformer_options["total_blocks"] = len(self.layers)
+        transformer_options["block_type"] = "double"
         img_input = img
         for i, layer in enumerate(self.layers):
+            transformer_options["block_index"] = i
             img = layer(img, mask, freqs_cis, adaln_input, transformer_options=transformer_options)
             if "double_block" in patches:
                 for p in patches["double_block"]:

comfy/ldm/qwen_image/model.py

@@ -322,6 +322,7 @@ class QwenImageTransformer2DModel(nn.Module):
         pooled_projection_dim: int = 768,
         guidance_embeds: bool = False,
         axes_dims_rope: Tuple[int, int, int] = (16, 56, 56),
+        default_ref_method="index",
         image_model=None,
         final_layer=True,
         dtype=None,
@@ -334,6 +335,7 @@ class QwenImageTransformer2DModel(nn.Module):
         self.in_channels = in_channels
         self.out_channels = out_channels or in_channels
         self.inner_dim = num_attention_heads * attention_head_dim
+        self.default_ref_method = default_ref_method
 
         self.pe_embedder = EmbedND(dim=attention_head_dim, theta=10000, axes_dim=list(axes_dims_rope))
 
@@ -361,6 +363,9 @@ class QwenImageTransformer2DModel(nn.Module):
             for _ in range(num_layers)
         ])
 
+        if self.default_ref_method == "index_timestep_zero":
+            self.register_buffer("__index_timestep_zero__", torch.tensor([]))
+
         if final_layer:
             self.norm_out = LastLayer(self.inner_dim, self.inner_dim, dtype=dtype, device=device, operations=operations)
             self.proj_out = operations.Linear(self.inner_dim, patch_size * patch_size * self.out_channels, bias=True, dtype=dtype, device=device)
@@ -416,7 +421,7 @@ class QwenImageTransformer2DModel(nn.Module):
             h = 0
             w = 0
             index = 0
-            ref_method = kwargs.get("ref_latents_method", "index")
+            ref_method = kwargs.get("ref_latents_method", self.default_ref_method)
             index_ref_method = (ref_method == "index") or (ref_method == "index_timestep_zero")
             timestep_zero = ref_method == "index_timestep_zero"
             for ref in ref_latents:

comfy/ldm/wan/model.py

@@ -568,7 +568,10 @@ class WanModel(torch.nn.Module):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
@@ -763,7 +766,10 @@ class VaceWanModel(WanModel):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
@@ -862,7 +868,10 @@ class CameraWanModel(WanModel):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
@@ -1326,16 +1335,19 @@ class WanModel_S2V(WanModel):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}
-                    out["img"] = block(args["img"], context=args["txt"], e=args["vec"], freqs=args["pe"])
+                    out["img"] = block(args["img"], context=args["txt"], e=args["vec"], freqs=args["pe"], transformer_options=args["transformer_options"])
                     return out
-                out = blocks_replace[("double_block", i)]({"img": x, "txt": context, "vec": e0, "pe": freqs}, {"original_block": block_wrap})
+                out = blocks_replace[("double_block", i)]({"img": x, "txt": context, "vec": e0, "pe": freqs, "transformer_options": transformer_options}, {"original_block": block_wrap})
                 x = out["img"]
             else:
-                x = block(x, e=e0, freqs=freqs, context=context)
+                x = block(x, e=e0, freqs=freqs, context=context, transformer_options=transformer_options)
             if audio_emb is not None:
                 x = self.audio_injector(x, i, audio_emb, audio_emb_global, seq_len)
         # head
@@ -1574,7 +1586,10 @@ class HumoWanModel(WanModel):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}

comfy/ldm/wan/model_animate.py

@@ -523,7 +523,10 @@ class AnimateWanModel(WanModel):
 
         patches_replace = transformer_options.get("patches_replace", {})
         blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.blocks)
+        transformer_options["block_type"] = "double"
         for i, block in enumerate(self.blocks):
+            transformer_options["block_index"] = i
             if ("double_block", i) in blocks_replace:
                 def block_wrap(args):
                     out = {}

comfy/model_detection.py

@@ -259,7 +259,7 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
                 dit_config["nerf_tile_size"] = 512
                 dit_config["nerf_final_head_type"] = "conv" if f"{key_prefix}nerf_final_layer_conv.norm.scale" in state_dict_keys else "linear"
                 dit_config["nerf_embedder_dtype"] = torch.float32
-                if "__x0__" in state_dict_keys: # x0 pred
+                if "{}__x0__".format(key_prefix) in state_dict_keys: # x0 pred
                     dit_config["use_x0"] = True
                 else:
                     dit_config["use_x0"] = False
@@ -618,6 +618,8 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
         dit_config["image_model"] = "qwen_image"
         dit_config["in_channels"] = state_dict['{}img_in.weight'.format(key_prefix)].shape[1]
         dit_config["num_layers"] = count_blocks(state_dict_keys, '{}transformer_blocks.'.format(key_prefix) + '{}.')
+        if "{}__index_timestep_zero__".format(key_prefix) in state_dict_keys:  # 2511
+            dit_config["default_ref_method"] = "index_timestep_zero"
         return dit_config
 
     if '{}visual_transformer_blocks.0.cross_attention.key_norm.weight'.format(key_prefix) in state_dict_keys: # Kandinsky 5

comfy/samplers.py

@@ -720,7 +720,7 @@ class Sampler:
         sigma = float(sigmas[0])
         return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma
 
-KSAMPLER_NAMES = ["euler", "euler_cfg_pp", "euler_ancestral", "euler_ancestral_cfg_pp", "heun", "heunpp2","dpm_2", "dpm_2_ancestral",
+KSAMPLER_NAMES = ["euler", "euler_cfg_pp", "euler_ancestral", "euler_ancestral_cfg_pp", "heun", "heunpp2", "exp_heun_2_x0", "exp_heun_2_x0_sde", "dpm_2", "dpm_2_ancestral",
                   "lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_2s_ancestral_cfg_pp", "dpmpp_sde", "dpmpp_sde_gpu",
                   "dpmpp_2m", "dpmpp_2m_cfg_pp", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_2m_sde_heun", "dpmpp_2m_sde_heun_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm",
                   "ipndm", "ipndm_v", "deis", "res_multistep", "res_multistep_cfg_pp", "res_multistep_ancestral", "res_multistep_ancestral_cfg_pp",

comfy/supported_models.py

@@ -28,6 +28,7 @@ from . import supported_models_base
 from . import latent_formats
 
 from . import diffusers_convert
+import comfy.model_management
 
 class SD15(supported_models_base.BASE):
     unet_config = {
@@ -1028,7 +1029,13 @@ class ZImage(Lumina2):
 
     memory_usage_factor = 2.0
 
-    supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32]
+    supported_inference_dtypes = [torch.bfloat16, torch.float32]
+
+    def __init__(self, unet_config):
+        super().__init__(unet_config)
+        if comfy.model_management.extended_fp16_support():
+            self.supported_inference_dtypes = self.supported_inference_dtypes.copy()
+            self.supported_inference_dtypes.insert(1, torch.float16)
 
     def clip_target(self, state_dict={}):
         pref = self.text_encoder_key_prefix[0]

comfy_api/latest/_io.py

@@ -1556,12 +1556,12 @@ class _ComfyNodeBaseInternal(_ComfyNodeInternal):
 
     @final
     @classmethod
-    def PREPARE_CLASS_CLONE(cls, v3_data: V3Data) -> type[ComfyNode]:
+    def PREPARE_CLASS_CLONE(cls, v3_data: V3Data | None) -> type[ComfyNode]:
         """Creates clone of real node class to prevent monkey-patching."""
         c_type: type[ComfyNode] = cls if is_class(cls) else type(cls)
         type_clone: type[ComfyNode] = shallow_clone_class(c_type)
         # set hidden
-        type_clone.hidden = HiddenHolder.from_dict(v3_data["hidden_inputs"])
+        type_clone.hidden = HiddenHolder.from_dict(v3_data["hidden_inputs"] if v3_data else None)
         return type_clone
 
     @final

comfy_api_nodes/apis/openai_api.py

@@ -0,0 +1,52 @@
+from pydantic import BaseModel, Field
+
+
+class Datum2(BaseModel):
+    b64_json: str | None = Field(None, description="Base64 encoded image data")
+    revised_prompt: str | None = Field(None, description="Revised prompt")
+    url: str | None = Field(None, description="URL of the image")
+
+
+class InputTokensDetails(BaseModel):
+    image_tokens: int | None = None
+    text_tokens: int | None = None
+
+
+class Usage(BaseModel):
+    input_tokens: int | None = None
+    input_tokens_details: InputTokensDetails | None = None
+    output_tokens: int | None = None
+    total_tokens: int | None = None
+
+
+class OpenAIImageGenerationResponse(BaseModel):
+    data: list[Datum2] | None = None
+    usage: Usage | None = None
+
+
+class OpenAIImageEditRequest(BaseModel):
+    background: str | None = Field(None, description="Background transparency")
+    model: str = Field(...)
+    moderation: str | None = Field(None)
+    n: int | None = Field(None, description="The number of images to generate")
+    output_compression: int | None = Field(None, description="Compression level for JPEG or WebP (0-100)")
+    output_format: str | None = Field(None)
+    prompt: str = Field(...)
+    quality: str | None = Field(None, description="Size of the image (e.g., 1024x1024, 1536x1024, auto)")
+    size: str | None = Field(None, description="Size of the output image")
+
+
+class OpenAIImageGenerationRequest(BaseModel):
+    background: str | None = Field(None, description="Background transparency")
+    model: str | None = Field(None)
+    moderation: str | None = Field(None)
+    n: int | None = Field(
+        None,
+        description="The number of images to generate.",
+    )
+    output_compression: int | None = Field(None, description="Compression level for JPEG or WebP (0-100)")
+    output_format: str | None = Field(None)
+    prompt: str = Field(...)
+    quality: str | None = Field(None, description="The quality of the generated image")
+    size: str | None = Field(None, description="Size of the image (e.g., 1024x1024, 1536x1024, auto)")
+    style: str | None = Field(None, description="Style of the image (only for dall-e-3)")

comfy_api_nodes/apis/tripo_api.py

@@ -5,11 +5,17 @@ from typing import Optional, List, Dict, Any, Union
 from pydantic import BaseModel, Field, RootModel
 
 class TripoModelVersion(str, Enum):
+    v3_0_20250812 = 'v3.0-20250812'
     v2_5_20250123 = 'v2.5-20250123'
     v2_0_20240919 = 'v2.0-20240919'
     v1_4_20240625 = 'v1.4-20240625'
 
 
+class TripoGeometryQuality(str, Enum):
+    standard = 'standard'
+    detailed = 'detailed'
+
+
 class TripoTextureQuality(str, Enum):
     standard = 'standard'
     detailed = 'detailed'
@@ -61,14 +67,20 @@ class TripoSpec(str, Enum):
 class TripoAnimation(str, Enum):
     IDLE = "preset:idle"
     WALK = "preset:walk"
+    RUN = "preset:run"
+    DIVE = "preset:dive"
     CLIMB = "preset:climb"
     JUMP = "preset:jump"
-    RUN = "preset:run"
     SLASH = "preset:slash"
     SHOOT = "preset:shoot"
     HURT = "preset:hurt"
     FALL = "preset:fall"
     TURN = "preset:turn"
+    QUADRUPED_WALK = "preset:quadruped:walk"
+    HEXAPOD_WALK = "preset:hexapod:walk"
+    OCTOPOD_WALK = "preset:octopod:walk"
+    SERPENTINE_MARCH = "preset:serpentine:march"
+    AQUATIC_MARCH = "preset:aquatic:march"
 
 class TripoStylizeStyle(str, Enum):
     LEGO = "lego"
@@ -105,6 +117,11 @@ class TripoTaskStatus(str, Enum):
     BANNED = "banned"
     EXPIRED = "expired"
 
+class TripoFbxPreset(str, Enum):
+    BLENDER = "blender"
+    MIXAMO = "mixamo"
+    _3DSMAX = "3dsmax"
+
 class TripoFileTokenReference(BaseModel):
     type: Optional[str] = Field(None, description='The type of the reference')
     file_token: str
@@ -142,6 +159,7 @@ class TripoTextToModelRequest(BaseModel):
     model_seed: Optional[int] = Field(None, description='The seed for the model')
     texture_seed: Optional[int] = Field(None, description='The seed for the texture')
     texture_quality: Optional[TripoTextureQuality] = TripoTextureQuality.standard
+    geometry_quality: Optional[TripoGeometryQuality] = TripoGeometryQuality.standard
     style: Optional[TripoStyle] = None
     auto_size: Optional[bool] = Field(False, description='Whether to auto-size the model')
     quad: Optional[bool] = Field(False, description='Whether to apply quad to the generated model')
@@ -156,6 +174,7 @@ class TripoImageToModelRequest(BaseModel):
     model_seed: Optional[int] = Field(None, description='The seed for the model')
     texture_seed: Optional[int] = Field(None, description='The seed for the texture')
     texture_quality: Optional[TripoTextureQuality] = TripoTextureQuality.standard
+    geometry_quality: Optional[TripoGeometryQuality] = TripoGeometryQuality.standard
     texture_alignment: Optional[TripoTextureAlignment] = Field(TripoTextureAlignment.ORIGINAL_IMAGE, description='The texture alignment method')
     style: Optional[TripoStyle] = Field(None, description='The style to apply to the generated model')
     auto_size: Optional[bool] = Field(False, description='Whether to auto-size the model')
@@ -173,6 +192,7 @@ class TripoMultiviewToModelRequest(BaseModel):
     model_seed: Optional[int] = Field(None, description='The seed for the model')
     texture_seed: Optional[int] = Field(None, description='The seed for the texture')
     texture_quality: Optional[TripoTextureQuality] = TripoTextureQuality.standard
+    geometry_quality: Optional[TripoGeometryQuality] = TripoGeometryQuality.standard
     texture_alignment: Optional[TripoTextureAlignment] = TripoTextureAlignment.ORIGINAL_IMAGE
     auto_size: Optional[bool] = Field(False, description='Whether to auto-size the model')
     orientation: Optional[TripoOrientation] = Field(TripoOrientation.DEFAULT, description='The orientation for the model')
@@ -219,14 +239,24 @@ class TripoConvertModelRequest(BaseModel):
     type: TripoTaskType = Field(TripoTaskType.CONVERT_MODEL, description='Type of task')
     format: TripoConvertFormat = Field(..., description='The format to convert to')
     original_model_task_id: str = Field(..., description='The task ID of the original model')
-    quad: Optional[bool] = Field(False, description='Whether to apply quad to the model')
-    force_symmetry: Optional[bool] = Field(False, description='Whether to force symmetry')
-    face_limit: Optional[int] = Field(10000, description='The number of faces to limit the conversion to')
-    flatten_bottom: Optional[bool] = Field(False, description='Whether to flatten the bottom of the model')
-    flatten_bottom_threshold: Optional[float] = Field(0.01, description='The threshold for flattening the bottom')
-    texture_size: Optional[int] = Field(4096, description='The size of the texture')
+    quad: Optional[bool] = Field(None, description='Whether to apply quad to the model')
+    force_symmetry: Optional[bool] = Field(None, description='Whether to force symmetry')
+    face_limit: Optional[int] = Field(None, description='The number of faces to limit the conversion to')
+    flatten_bottom: Optional[bool] = Field(None, description='Whether to flatten the bottom of the model')
+    flatten_bottom_threshold: Optional[float] = Field(None, description='The threshold for flattening the bottom')
+    texture_size: Optional[int] = Field(None, description='The size of the texture')
     texture_format: Optional[TripoTextureFormat] = Field(TripoTextureFormat.JPEG, description='The format of the texture')
-    pivot_to_center_bottom: Optional[bool] = Field(False, description='Whether to pivot to the center bottom')
+    pivot_to_center_bottom: Optional[bool] = Field(None, description='Whether to pivot to the center bottom')
+    scale_factor: Optional[float] = Field(None, description='The scale factor for the model')
+    with_animation: Optional[bool] = Field(None, description='Whether to include animations')
+    pack_uv: Optional[bool] = Field(None, description='Whether to pack the UVs')
+    bake: Optional[bool] = Field(None, description='Whether to bake the model')
+    part_names: Optional[List[str]] = Field(None, description='The names of the parts to include')
+    fbx_preset: Optional[TripoFbxPreset] = Field(None, description='The preset for the FBX export')
+    export_vertex_colors: Optional[bool] = Field(None, description='Whether to export the vertex colors')
+    export_orientation: Optional[TripoOrientation] = Field(None, description='The orientation for the export')
+    animate_in_place: Optional[bool] = Field(None, description='Whether to animate in place')
+
 
 class TripoTaskRequest(RootModel):
     root: Union[

comfy_api_nodes/nodes_openai.py

@@ -1,46 +1,45 @@
-from io import BytesIO
+import base64
 import os
 from enum import Enum
-from inspect import cleandoc
+from io import BytesIO
+
 import numpy as np
 import torch
 from PIL import Image
-import folder_paths
-import base64
-from comfy_api.latest import IO, ComfyExtension
 from typing_extensions import override
 
-
+import folder_paths
+from comfy_api.latest import IO, ComfyExtension, Input
 from comfy_api_nodes.apis import (
-    OpenAIImageGenerationRequest,
-    OpenAIImageEditRequest,
-    OpenAIImageGenerationResponse,
-    OpenAICreateResponse,
-    OpenAIResponse,
     CreateModelResponseProperties,
-    Item,
-    OutputContent,
-    InputImageContent,
     Detail,
-    InputTextContent,
-    InputMessage,
-    InputMessageContentList,
     InputContent,
     InputFileContent,
+    InputImageContent,
+    InputMessage,
+    InputMessageContentList,
+    InputTextContent,
+    Item,
+    OpenAICreateResponse,
+    OpenAIResponse,
+    OutputContent,
+)
+from comfy_api_nodes.apis.openai_api import (
+    OpenAIImageEditRequest,
+    OpenAIImageGenerationRequest,
+    OpenAIImageGenerationResponse,
 )
-
 from comfy_api_nodes.util import (
-    downscale_image_tensor,
-    download_url_to_bytesio,
-    validate_string,
-    tensor_to_base64_string,
     ApiEndpoint,
-    sync_op,
+    download_url_to_bytesio,
+    downscale_image_tensor,
     poll_op,
+    sync_op,
+    tensor_to_base64_string,
     text_filepath_to_data_uri,
+    validate_string,
 )
 
-
 RESPONSES_ENDPOINT = "/proxy/openai/v1/responses"
 STARTING_POINT_ID_PATTERN = r"<starting_point_id:(.*)>"
 
@@ -98,9 +97,6 @@ async def validate_and_cast_response(response, timeout: int = None) -> torch.Ten
 
 
 class OpenAIDalle2(IO.ComfyNode):
-    """
-    Generates images synchronously via OpenAI's DALL·E 2 endpoint.
-    """
 
     @classmethod
     def define_schema(cls):
@@ -108,7 +104,7 @@ class OpenAIDalle2(IO.ComfyNode):
             node_id="OpenAIDalle2",
             display_name="OpenAI DALL·E 2",
             category="api node/image/OpenAI",
-            description=cleandoc(cls.__doc__ or ""),
+            description="Generates images synchronously via OpenAI's DALL·E 2 endpoint.",
             inputs=[
                 IO.String.Input(
                     "prompt",
@@ -234,9 +230,6 @@ class OpenAIDalle2(IO.ComfyNode):
 
 
 class OpenAIDalle3(IO.ComfyNode):
-    """
-    Generates images synchronously via OpenAI's DALL·E 3 endpoint.
-    """
 
     @classmethod
     def define_schema(cls):
@@ -244,7 +237,7 @@ class OpenAIDalle3(IO.ComfyNode):
             node_id="OpenAIDalle3",
             display_name="OpenAI DALL·E 3",
             category="api node/image/OpenAI",
-            description=cleandoc(cls.__doc__ or ""),
+            description="Generates images synchronously via OpenAI's DALL·E 3 endpoint.",
             inputs=[
                 IO.String.Input(
                     "prompt",
@@ -326,10 +319,16 @@ class OpenAIDalle3(IO.ComfyNode):
         return IO.NodeOutput(await validate_and_cast_response(response))
 
 
+def calculate_tokens_price_image_1(response: OpenAIImageGenerationResponse) -> float | None:
+    # https://platform.openai.com/docs/pricing
+    return ((response.usage.input_tokens * 10.0) + (response.usage.output_tokens * 40.0)) / 1_000_000.0
+
+
+def calculate_tokens_price_image_1_5(response: OpenAIImageGenerationResponse) -> float | None:
+    return ((response.usage.input_tokens * 8.0) + (response.usage.output_tokens * 32.0)) / 1_000_000.0
+
+
 class OpenAIGPTImage1(IO.ComfyNode):
-    """
-    Generates images synchronously via OpenAI's GPT Image 1 endpoint.
-    """
 
     @classmethod
     def define_schema(cls):
@@ -337,13 +336,13 @@ class OpenAIGPTImage1(IO.ComfyNode):
             node_id="OpenAIGPTImage1",
             display_name="OpenAI GPT Image 1",
             category="api node/image/OpenAI",
-            description=cleandoc(cls.__doc__ or ""),
+            description="Generates images synchronously via OpenAI's GPT Image 1 endpoint.",
             inputs=[
                 IO.String.Input(
                     "prompt",
                     default="",
                     multiline=True,
-                    tooltip="Text prompt for GPT Image 1",
+                    tooltip="Text prompt for GPT Image",
                 ),
                 IO.Int.Input(
                     "seed",
@@ -365,8 +364,8 @@ class OpenAIGPTImage1(IO.ComfyNode):
                 ),
                 IO.Combo.Input(
                     "background",
-                    default="opaque",
-                    options=["opaque", "transparent"],
+                    default="auto",
+                    options=["auto", "opaque", "transparent"],
                     tooltip="Return image with or without background",
                     optional=True,
                 ),
@@ -397,6 +396,11 @@ class OpenAIGPTImage1(IO.ComfyNode):
                     tooltip="Optional mask for inpainting (white areas will be replaced)",
                     optional=True,
                 ),
+                IO.Combo.Input(
+                    "model",
+                    options=["gpt-image-1", "gpt-image-1.5"],
+                    optional=True,
+                ),
             ],
             outputs=[
                 IO.Image.Output(),
@@ -412,32 +416,34 @@ class OpenAIGPTImage1(IO.ComfyNode):
     @classmethod
     async def execute(
         cls,
-        prompt,
-        seed=0,
-        quality="low",
-        background="opaque",
-        image=None,
-        mask=None,
-        n=1,
-        size="1024x1024",
+        prompt: str,
+        seed: int = 0,
+        quality: str = "low",
+        background: str = "opaque",
+        image: Input.Image | None = None,
+        mask: Input.Image | None = None,
+        n: int = 1,
+        size: str = "1024x1024",
+        model: str = "gpt-image-1",
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=False)
-        model = "gpt-image-1"
-        path = "/proxy/openai/images/generations"
-        content_type = "application/json"
-        request_class = OpenAIImageGenerationRequest
-        files = []
+
+        if mask is not None and image is None:
+            raise ValueError("Cannot use a mask without an input image")
+
+        if model == "gpt-image-1":
+            price_extractor = calculate_tokens_price_image_1
+        elif model == "gpt-image-1.5":
+            price_extractor = calculate_tokens_price_image_1_5
+        else:
+            raise ValueError(f"Unknown model: {model}")
 
         if image is not None:
-            path = "/proxy/openai/images/edits"
-            request_class = OpenAIImageEditRequest
-            content_type = "multipart/form-data"
-
+            files = []
             batch_size = image.shape[0]
-
             for i in range(batch_size):
-                single_image = image[i : i + 1]
-                scaled_image = downscale_image_tensor(single_image).squeeze()
+                single_image = image[i: i + 1]
+                scaled_image = downscale_image_tensor(single_image, total_pixels=2048*2048).squeeze()
 
                 image_np = (scaled_image.numpy() * 255).astype(np.uint8)
                 img = Image.fromarray(image_np)
@@ -450,44 +456,59 @@ class OpenAIGPTImage1(IO.ComfyNode):
                 else:
                     files.append(("image[]", (f"image_{i}.png", img_byte_arr, "image/png")))
 
-        if mask is not None:
-            if image is None:
-                raise Exception("Cannot use a mask without an input image")
-            if image.shape[0] != 1:
-                raise Exception("Cannot use a mask with multiple image")
-            if mask.shape[1:] != image.shape[1:-1]:
-                raise Exception("Mask and Image must be the same size")
-            batch, height, width = mask.shape
-            rgba_mask = torch.zeros(height, width, 4, device="cpu")
-            rgba_mask[:, :, 3] = 1 - mask.squeeze().cpu()
+            if mask is not None:
+                if image.shape[0] != 1:
+                    raise Exception("Cannot use a mask with multiple image")
+                if mask.shape[1:] != image.shape[1:-1]:
+                    raise Exception("Mask and Image must be the same size")
+                _, height, width = mask.shape
+                rgba_mask = torch.zeros(height, width, 4, device="cpu")
+                rgba_mask[:, :, 3] = 1 - mask.squeeze().cpu()
 
-            scaled_mask = downscale_image_tensor(rgba_mask.unsqueeze(0)).squeeze()
+                scaled_mask = downscale_image_tensor(rgba_mask.unsqueeze(0), total_pixels=2048*2048).squeeze()
 
-            mask_np = (scaled_mask.numpy() * 255).astype(np.uint8)
-            mask_img = Image.fromarray(mask_np)
-            mask_img_byte_arr = BytesIO()
-            mask_img.save(mask_img_byte_arr, format="PNG")
-            mask_img_byte_arr.seek(0)
-            files.append(("mask", ("mask.png", mask_img_byte_arr, "image/png")))
-
-        # Build the operation
-        response = await sync_op(
-            cls,
-            ApiEndpoint(path=path, method="POST"),
-            response_model=OpenAIImageGenerationResponse,
-            data=request_class(
-                model=model,
-                prompt=prompt,
-                quality=quality,
-                background=background,
-                n=n,
-                seed=seed,
-                size=size,
-            ),
-            files=files if files else None,
-            content_type=content_type,
-        )
+                mask_np = (scaled_mask.numpy() * 255).astype(np.uint8)
+                mask_img = Image.fromarray(mask_np)
+                mask_img_byte_arr = BytesIO()
+                mask_img.save(mask_img_byte_arr, format="PNG")
+                mask_img_byte_arr.seek(0)
+                files.append(("mask", ("mask.png", mask_img_byte_arr, "image/png")))
 
+            response = await sync_op(
+                cls,
+                ApiEndpoint(path="/proxy/openai/images/edits", method="POST"),
+                response_model=OpenAIImageGenerationResponse,
+                data=OpenAIImageEditRequest(
+                    model=model,
+                    prompt=prompt,
+                    quality=quality,
+                    background=background,
+                    n=n,
+                    seed=seed,
+                    size=size,
+                    moderation="low",
+                ),
+                content_type="multipart/form-data",
+                files=files,
+                price_extractor=price_extractor,
+            )
+        else:
+            response = await sync_op(
+                cls,
+                ApiEndpoint(path="/proxy/openai/images/generations", method="POST"),
+                response_model=OpenAIImageGenerationResponse,
+                data=OpenAIImageGenerationRequest(
+                    model=model,
+                    prompt=prompt,
+                    quality=quality,
+                    background=background,
+                    n=n,
+                    seed=seed,
+                    size=size,
+                    moderation="low",
+                ),
+                price_extractor=price_extractor,
+            )
         return IO.NodeOutput(await validate_and_cast_response(response))
 
 

comfy_api_nodes/nodes_tripo.py

@@ -102,8 +102,9 @@ class TripoTextToModelNode(IO.ComfyNode):
                 IO.Int.Input("model_seed", default=42, optional=True),
                 IO.Int.Input("texture_seed", default=42, optional=True),
                 IO.Combo.Input("texture_quality", default="standard", options=["standard", "detailed"], optional=True),
-                IO.Int.Input("face_limit", default=-1, min=-1, max=500000, optional=True),
+                IO.Int.Input("face_limit", default=-1, min=-1, max=2000000, optional=True),
                 IO.Boolean.Input("quad", default=False, optional=True),
+                IO.Combo.Input("geometry_quality", default="standard", options=["standard", "detailed"], optional=True),
             ],
             outputs=[
                 IO.String.Output(display_name="model_file"),
@@ -131,6 +132,7 @@ class TripoTextToModelNode(IO.ComfyNode):
         model_seed: Optional[int] = None,
         texture_seed: Optional[int] = None,
         texture_quality: Optional[str] = None,
+        geometry_quality: Optional[str] = None,
         face_limit: Optional[int] = None,
         quad: Optional[bool] = None,
     ) -> IO.NodeOutput:
@@ -154,6 +156,7 @@ class TripoTextToModelNode(IO.ComfyNode):
                 texture_seed=texture_seed,
                 texture_quality=texture_quality,
                 face_limit=face_limit,
+                geometry_quality=geometry_quality,
                 auto_size=True,
                 quad=quad,
             ),
@@ -194,6 +197,7 @@ class TripoImageToModelNode(IO.ComfyNode):
                 ),
                 IO.Int.Input("face_limit", default=-1, min=-1, max=500000, optional=True),
                 IO.Boolean.Input("quad", default=False, optional=True),
+                IO.Combo.Input("geometry_quality", default="standard", options=["standard", "detailed"], optional=True),
             ],
             outputs=[
                 IO.String.Output(display_name="model_file"),
@@ -220,6 +224,7 @@ class TripoImageToModelNode(IO.ComfyNode):
         orientation=None,
         texture_seed: Optional[int] = None,
         texture_quality: Optional[str] = None,
+        geometry_quality: Optional[str] = None,
         texture_alignment: Optional[str] = None,
         face_limit: Optional[int] = None,
         quad: Optional[bool] = None,
@@ -246,6 +251,7 @@ class TripoImageToModelNode(IO.ComfyNode):
                 pbr=pbr,
                 model_seed=model_seed,
                 orientation=orientation,
+                geometry_quality=geometry_quality,
                 texture_alignment=texture_alignment,
                 texture_seed=texture_seed,
                 texture_quality=texture_quality,
@@ -295,6 +301,7 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
                 ),
                 IO.Int.Input("face_limit", default=-1, min=-1, max=500000, optional=True),
                 IO.Boolean.Input("quad", default=False, optional=True),
+                IO.Combo.Input("geometry_quality", default="standard", options=["standard", "detailed"], optional=True),
             ],
             outputs=[
                 IO.String.Output(display_name="model_file"),
@@ -323,6 +330,7 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
         model_seed: Optional[int] = None,
         texture_seed: Optional[int] = None,
         texture_quality: Optional[str] = None,
+        geometry_quality: Optional[str] = None,
         texture_alignment: Optional[str] = None,
         face_limit: Optional[int] = None,
         quad: Optional[bool] = None,
@@ -359,6 +367,7 @@ class TripoMultiviewToModelNode(IO.ComfyNode):
                 model_seed=model_seed,
                 texture_seed=texture_seed,
                 texture_quality=texture_quality,
+                geometry_quality=geometry_quality,
                 texture_alignment=texture_alignment,
                 face_limit=face_limit,
                 quad=quad,
@@ -508,6 +517,8 @@ class TripoRetargetNode(IO.ComfyNode):
                     options=[
                         "preset:idle",
                         "preset:walk",
+                        "preset:run",
+                        "preset:dive",
                         "preset:climb",
                         "preset:jump",
                         "preset:slash",
@@ -515,6 +526,11 @@ class TripoRetargetNode(IO.ComfyNode):
                         "preset:hurt",
                         "preset:fall",
                         "preset:turn",
+                        "preset:quadruped:walk",
+                        "preset:hexapod:walk",
+                        "preset:octopod:walk",
+                        "preset:serpentine:march",
+                        "preset:aquatic:march"
                     ],
                 ),
             ],
@@ -563,7 +579,7 @@ class TripoConversionNode(IO.ComfyNode):
                     "face_limit",
                     default=-1,
                     min=-1,
-                    max=500000,
+                    max=2000000,
                     optional=True,
                 ),
                 IO.Int.Input(
@@ -579,6 +595,40 @@ class TripoConversionNode(IO.ComfyNode):
                     default="JPEG",
                     optional=True,
                 ),
+                IO.Boolean.Input("force_symmetry", default=False, optional=True),
+                IO.Boolean.Input("flatten_bottom", default=False, optional=True),
+                IO.Float.Input(
+                    "flatten_bottom_threshold",
+                    default=0.0,
+                    min=0.0,
+                    max=1.0,
+                    optional=True,
+                ),
+                IO.Boolean.Input("pivot_to_center_bottom", default=False, optional=True),
+                IO.Float.Input(
+                    "scale_factor",
+                    default=1.0,
+                    min=0.0,
+                    optional=True,
+                ),
+                IO.Boolean.Input("with_animation", default=False, optional=True),
+                IO.Boolean.Input("pack_uv", default=False, optional=True),
+                IO.Boolean.Input("bake", default=False, optional=True),
+                IO.String.Input("part_names", default="", optional=True),  # comma-separated list
+                IO.Combo.Input(
+                    "fbx_preset",
+                    options=["blender", "mixamo", "3dsmax"],
+                    default="blender",
+                    optional=True,
+                ),
+                IO.Boolean.Input("export_vertex_colors", default=False, optional=True),
+                IO.Combo.Input(
+                    "export_orientation",
+                    options=["align_image", "default"],
+                    default="default",
+                    optional=True,
+                ),
+                IO.Boolean.Input("animate_in_place", default=False, optional=True),
             ],
             outputs=[],
             hidden=[
@@ -604,12 +654,31 @@ class TripoConversionNode(IO.ComfyNode):
         original_model_task_id,
         format: str,
         quad: bool,
+        force_symmetry: bool,
         face_limit: int,
+        flatten_bottom: bool,
+        flatten_bottom_threshold: float,
         texture_size: int,
         texture_format: str,
+        pivot_to_center_bottom: bool,
+        scale_factor: float,
+        with_animation: bool,
+        pack_uv: bool,
+        bake: bool,
+        part_names: str,
+        fbx_preset: str,
+        export_vertex_colors: bool,
+        export_orientation: str,
+        animate_in_place: bool,
     ) -> IO.NodeOutput:
         if not original_model_task_id:
             raise RuntimeError("original_model_task_id is required")
+
+        # Parse part_names from comma-separated string to list
+        part_names_list = None
+        if part_names and part_names.strip():
+            part_names_list = [name.strip() for name in part_names.split(',') if name.strip()]
+
         response = await sync_op(
             cls,
             endpoint=ApiEndpoint(path="/proxy/tripo/v2/openapi/task", method="POST"),
@@ -618,9 +687,22 @@ class TripoConversionNode(IO.ComfyNode):
                 original_model_task_id=original_model_task_id,
                 format=format,
                 quad=quad if quad else None,
+                force_symmetry=force_symmetry if force_symmetry else None,
                 face_limit=face_limit if face_limit != -1 else None,
+                flatten_bottom=flatten_bottom if flatten_bottom else None,
+                flatten_bottom_threshold=flatten_bottom_threshold if flatten_bottom_threshold != 0.0 else None,
                 texture_size=texture_size if texture_size != 4096 else None,
                 texture_format=texture_format if texture_format != "JPEG" else None,
+                pivot_to_center_bottom=pivot_to_center_bottom if pivot_to_center_bottom else None,
+                scale_factor=scale_factor if scale_factor != 1.0 else None,
+                with_animation=with_animation if with_animation else None,
+                pack_uv=pack_uv if pack_uv else None,
+                bake=bake if bake else None,
+                part_names=part_names_list,
+                fbx_preset=fbx_preset if fbx_preset != "blender" else None,
+                export_vertex_colors=export_vertex_colors if export_vertex_colors else None,
+                export_orientation=export_orientation if export_orientation != "default" else None,
+                animate_in_place=animate_in_place if animate_in_place else None,
             ),
         )
         return await poll_until_finished(cls, response, average_duration=30)

comfy_api_nodes/nodes_wan.py

@@ -1,7 +1,5 @@
 import re
-from typing import Optional
 
-import torch
 from pydantic import BaseModel, Field
 from typing_extensions import override
 
@@ -21,26 +19,26 @@ from comfy_api_nodes.util import (
 
 class Text2ImageInputField(BaseModel):
     prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
+    negative_prompt: str | None = Field(None)
 
 
 class Image2ImageInputField(BaseModel):
     prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
+    negative_prompt: str | None = Field(None)
     images: list[str] = Field(..., min_length=1, max_length=2)
 
 
 class Text2VideoInputField(BaseModel):
     prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
-    audio_url: Optional[str] = Field(None)
+    negative_prompt: str | None = Field(None)
+    audio_url: str | None = Field(None)
 
 
 class Image2VideoInputField(BaseModel):
     prompt: str = Field(...)
-    negative_prompt: Optional[str] = Field(None)
+    negative_prompt: str | None = Field(None)
     img_url: str = Field(...)
-    audio_url: Optional[str] = Field(None)
+    audio_url: str | None = Field(None)
 
 
 class Txt2ImageParametersField(BaseModel):
@@ -52,7 +50,7 @@ class Txt2ImageParametersField(BaseModel):
 
 
 class Image2ImageParametersField(BaseModel):
-    size: Optional[str] = Field(None)
+    size: str | None = 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)
@@ -61,19 +59,21 @@ class Image2ImageParametersField(BaseModel):
 class Text2VideoParametersField(BaseModel):
     size: str = Field(...)
     seed: int = Field(..., ge=0, le=2147483647)
-    duration: int = Field(5, ge=5, le=10)
+    duration: int = Field(5, ge=5, le=15)
     prompt_extend: bool = Field(True)
     watermark: bool = Field(True)
-    audio: bool = Field(False, description="Should be audio generated automatically")
+    audio: bool = Field(False, description="Whether to generate audio automatically.")
+    shot_type: str = Field("single")
 
 
 class Image2VideoParametersField(BaseModel):
     resolution: str = Field(...)
     seed: int = Field(..., ge=0, le=2147483647)
-    duration: int = Field(5, ge=5, le=10)
+    duration: int = Field(5, ge=5, le=15)
     prompt_extend: bool = Field(True)
     watermark: bool = Field(True)
-    audio: bool = Field(False, description="Should be audio generated automatically")
+    audio: bool = Field(False, description="Whether to generate audio automatically.")
+    shot_type: str = Field("single")
 
 
 class Text2ImageTaskCreationRequest(BaseModel):
@@ -106,39 +106,39 @@ class TaskCreationOutputField(BaseModel):
 
 
 class TaskCreationResponse(BaseModel):
-    output: Optional[TaskCreationOutputField] = Field(None)
+    output: TaskCreationOutputField | None = Field(None)
     request_id: str = Field(...)
-    code: Optional[str] = Field(None, description="The error code of the failed request.")
-    message: Optional[str] = Field(None, description="Details of the failed request.")
+    code: str | None = Field(None, description="Error code for the failed request.")
+    message: str | None = Field(None, description="Details about the failed request.")
 
 
 class TaskResult(BaseModel):
-    url: Optional[str] = Field(None)
-    code: Optional[str] = Field(None)
-    message: Optional[str] = Field(None)
+    url: str | None = Field(None)
+    code: str | None = Field(None)
+    message: str | None = Field(None)
 
 
 class ImageTaskStatusOutputField(TaskCreationOutputField):
     task_id: str = Field(...)
     task_status: str = Field(...)
-    results: Optional[list[TaskResult]] = Field(None)
+    results: list[TaskResult] | None = Field(None)
 
 
 class VideoTaskStatusOutputField(TaskCreationOutputField):
     task_id: str = Field(...)
     task_status: str = Field(...)
-    video_url: Optional[str] = Field(None)
-    code: Optional[str] = Field(None)
-    message: Optional[str] = Field(None)
+    video_url: str | None = Field(None)
+    code: str | None = Field(None)
+    message: str | None = Field(None)
 
 
 class ImageTaskStatusResponse(BaseModel):
-    output: Optional[ImageTaskStatusOutputField] = Field(None)
+    output: ImageTaskStatusOutputField | None = Field(None)
     request_id: str = Field(...)
 
 
 class VideoTaskStatusResponse(BaseModel):
-    output: Optional[VideoTaskStatusOutputField] = Field(None)
+    output: VideoTaskStatusOutputField | None = Field(None)
     request_id: str = Field(...)
 
 
@@ -152,7 +152,7 @@ class WanTextToImageApi(IO.ComfyNode):
             node_id="WanTextToImageApi",
             display_name="Wan Text to Image",
             category="api node/image/Wan",
-            description="Generates image based on text prompt.",
+            description="Generates an image based on a text prompt.",
             inputs=[
                 IO.Combo.Input(
                     "model",
@@ -164,13 +164,13 @@ class WanTextToImageApi(IO.ComfyNode):
                     "prompt",
                     multiline=True,
                     default="",
-                    tooltip="Prompt used to describe the elements and visual features, supports English/Chinese.",
+                    tooltip="Prompt describing the elements and visual features. Supports English and Chinese.",
                 ),
                 IO.String.Input(
                     "negative_prompt",
                     multiline=True,
                     default="",
-                    tooltip="Negative text prompt to guide what to avoid.",
+                    tooltip="Negative prompt describing what to avoid.",
                     optional=True,
                 ),
                 IO.Int.Input(
@@ -209,7 +209,7 @@ class WanTextToImageApi(IO.ComfyNode):
                 IO.Boolean.Input(
                     "watermark",
                     default=True,
-                    tooltip='Whether to add an "AI generated" watermark to the result.',
+                    tooltip="Whether to add an AI-generated watermark to the result.",
                     optional=True,
                 ),
             ],
@@ -252,7 +252,7 @@ class WanTextToImageApi(IO.ComfyNode):
             ),
         )
         if not initial_response.output:
-            raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
         response = await poll_op(
             cls,
             ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
@@ -272,7 +272,7 @@ class WanImageToImageApi(IO.ComfyNode):
             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).",
+            "The output image is currently fixed at 1.6 MP, and its aspect ratio matches the input image(s).",
             inputs=[
                 IO.Combo.Input(
                     "model",
@@ -282,19 +282,19 @@ class WanImageToImageApi(IO.ComfyNode):
                 ),
                 IO.Image.Input(
                     "image",
-                    tooltip="Single-image editing or multi-image fusion, maximum 2 images.",
+                    tooltip="Single-image editing or multi-image fusion. Maximum 2 images.",
                 ),
                 IO.String.Input(
                     "prompt",
                     multiline=True,
                     default="",
-                    tooltip="Prompt used to describe the elements and visual features, supports English/Chinese.",
+                    tooltip="Prompt describing the elements and visual features. Supports English and Chinese.",
                 ),
                 IO.String.Input(
                     "negative_prompt",
                     multiline=True,
                     default="",
-                    tooltip="Negative text prompt to guide what to avoid.",
+                    tooltip="Negative prompt describing what to avoid.",
                     optional=True,
                 ),
                 # redo this later as an optional combo of recommended resolutions
@@ -328,7 +328,7 @@ class WanImageToImageApi(IO.ComfyNode):
                 IO.Boolean.Input(
                     "watermark",
                     default=True,
-                    tooltip='Whether to add an "AI generated" watermark to the result.',
+                    tooltip="Whether to add an AI-generated watermark to the result.",
                     optional=True,
                 ),
             ],
@@ -347,7 +347,7 @@ class WanImageToImageApi(IO.ComfyNode):
     async def execute(
         cls,
         model: str,
-        image: torch.Tensor,
+        image: Input.Image,
         prompt: str,
         negative_prompt: str = "",
         # width: int = 1024,
@@ -357,7 +357,7 @@ class WanImageToImageApi(IO.ComfyNode):
     ):
         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}.")
+            raise ValueError(f"Expected 1 or 2 input images, but got {n_images}.")
         images = []
         for i in image:
             images.append("data:image/png;base64," + tensor_to_base64_string(i, total_pixels=4096 * 4096))
@@ -376,7 +376,7 @@ class WanImageToImageApi(IO.ComfyNode):
             ),
         )
         if not initial_response.output:
-            raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
         response = await poll_op(
             cls,
             ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
@@ -395,25 +395,25 @@ class WanTextToVideoApi(IO.ComfyNode):
             node_id="WanTextToVideoApi",
             display_name="Wan Text to Video",
             category="api node/video/Wan",
-            description="Generates video based on text prompt.",
+            description="Generates a video based on a text prompt.",
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=["wan2.5-t2v-preview"],
-                    default="wan2.5-t2v-preview",
+                    options=["wan2.5-t2v-preview", "wan2.6-t2v"],
+                    default="wan2.6-t2v",
                     tooltip="Model to use.",
                 ),
                 IO.String.Input(
                     "prompt",
                     multiline=True,
                     default="",
-                    tooltip="Prompt used to describe the elements and visual features, supports English/Chinese.",
+                    tooltip="Prompt describing the elements and visual features. Supports English and Chinese.",
                 ),
                 IO.String.Input(
                     "negative_prompt",
                     multiline=True,
                     default="",
-                    tooltip="Negative text prompt to guide what to avoid.",
+                    tooltip="Negative prompt describing what to avoid.",
                     optional=True,
                 ),
                 IO.Combo.Input(
@@ -433,23 +433,23 @@ class WanTextToVideoApi(IO.ComfyNode):
                         "1080p: 4:3 (1632x1248)",
                         "1080p: 3:4 (1248x1632)",
                     ],
-                    default="480p: 1:1 (624x624)",
+                    default="720p: 1:1 (960x960)",
                     optional=True,
                 ),
                 IO.Int.Input(
                     "duration",
                     default=5,
                     min=5,
-                    max=10,
+                    max=15,
                     step=5,
                     display_mode=IO.NumberDisplay.number,
-                    tooltip="Available durations: 5 and 10 seconds",
+                    tooltip="A 15-second duration is available only for the Wan 2.6 model.",
                     optional=True,
                 ),
                 IO.Audio.Input(
                     "audio",
                     optional=True,
-                    tooltip="Audio must contain a clear, loud voice, without extraneous noise, background music.",
+                    tooltip="Audio must contain a clear, loud voice, without extraneous noise or background music.",
                 ),
                 IO.Int.Input(
                     "seed",
@@ -466,7 +466,7 @@ class WanTextToVideoApi(IO.ComfyNode):
                     "generate_audio",
                     default=False,
                     optional=True,
-                    tooltip="If there is no audio input, generate audio automatically.",
+                    tooltip="If no audio input is provided, generate audio automatically.",
                 ),
                 IO.Boolean.Input(
                     "prompt_extend",
@@ -477,7 +477,15 @@ class WanTextToVideoApi(IO.ComfyNode):
                 IO.Boolean.Input(
                     "watermark",
                     default=True,
-                    tooltip='Whether to add an "AI generated" watermark to the result.',
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    optional=True,
+                ),
+                IO.Combo.Input(
+                    "shot_type",
+                    options=["single", "multi"],
+                    tooltip="Specifies the shot type for the generated video, that is, whether the video is a "
+                    "single continuous shot or multiple shots with cuts. "
+                    "This parameter takes effect only when prompt_extend is True.",
                     optional=True,
                 ),
             ],
@@ -498,14 +506,19 @@ class WanTextToVideoApi(IO.ComfyNode):
         model: str,
         prompt: str,
         negative_prompt: str = "",
-        size: str = "480p: 1:1 (624x624)",
+        size: str = "720p: 1:1 (960x960)",
         duration: int = 5,
-        audio: Optional[Input.Audio] = None,
+        audio: Input.Audio | None = None,
         seed: int = 0,
         generate_audio: bool = False,
         prompt_extend: bool = True,
         watermark: bool = True,
+        shot_type: str = "single",
     ):
+        if "480p" in size and model == "wan2.6-t2v":
+            raise ValueError("The Wan 2.6 model does not support 480p.")
+        if duration == 15 and model == "wan2.5-t2v-preview":
+            raise ValueError("A 15-second duration is supported only by the Wan 2.6 model.")
         width, height = RES_IN_PARENS.search(size).groups()
         audio_url = None
         if audio is not None:
@@ -526,11 +539,12 @@ class WanTextToVideoApi(IO.ComfyNode):
                     audio=generate_audio,
                     prompt_extend=prompt_extend,
                     watermark=watermark,
+                    shot_type=shot_type,
                 ),
             ),
         )
         if not initial_response.output:
-            raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
         response = await poll_op(
             cls,
             ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),
@@ -549,12 +563,12 @@ class WanImageToVideoApi(IO.ComfyNode):
             node_id="WanImageToVideoApi",
             display_name="Wan Image to Video",
             category="api node/video/Wan",
-            description="Generates video based on the first frame and text prompt.",
+            description="Generates a video from the first frame and a text prompt.",
             inputs=[
                 IO.Combo.Input(
                     "model",
-                    options=["wan2.5-i2v-preview"],
-                    default="wan2.5-i2v-preview",
+                    options=["wan2.5-i2v-preview", "wan2.6-i2v"],
+                    default="wan2.6-i2v",
                     tooltip="Model to use.",
                 ),
                 IO.Image.Input(
@@ -564,13 +578,13 @@ class WanImageToVideoApi(IO.ComfyNode):
                     "prompt",
                     multiline=True,
                     default="",
-                    tooltip="Prompt used to describe the elements and visual features, supports English/Chinese.",
+                    tooltip="Prompt describing the elements and visual features. Supports English and Chinese.",
                 ),
                 IO.String.Input(
                     "negative_prompt",
                     multiline=True,
                     default="",
-                    tooltip="Negative text prompt to guide what to avoid.",
+                    tooltip="Negative prompt describing what to avoid.",
                     optional=True,
                 ),
                 IO.Combo.Input(
@@ -580,23 +594,23 @@ class WanImageToVideoApi(IO.ComfyNode):
                         "720P",
                         "1080P",
                     ],
-                    default="480P",
+                    default="720P",
                     optional=True,
                 ),
                 IO.Int.Input(
                     "duration",
                     default=5,
                     min=5,
-                    max=10,
+                    max=15,
                     step=5,
                     display_mode=IO.NumberDisplay.number,
-                    tooltip="Available durations: 5 and 10 seconds",
+                    tooltip="Duration 15 available only for WAN2.6 model.",
                     optional=True,
                 ),
                 IO.Audio.Input(
                     "audio",
                     optional=True,
-                    tooltip="Audio must contain a clear, loud voice, without extraneous noise, background music.",
+                    tooltip="Audio must contain a clear, loud voice, without extraneous noise or background music.",
                 ),
                 IO.Int.Input(
                     "seed",
@@ -613,7 +627,7 @@ class WanImageToVideoApi(IO.ComfyNode):
                     "generate_audio",
                     default=False,
                     optional=True,
-                    tooltip="If there is no audio input, generate audio automatically.",
+                    tooltip="If no audio input is provided, generate audio automatically.",
                 ),
                 IO.Boolean.Input(
                     "prompt_extend",
@@ -624,7 +638,15 @@ class WanImageToVideoApi(IO.ComfyNode):
                 IO.Boolean.Input(
                     "watermark",
                     default=True,
-                    tooltip='Whether to add an "AI generated" watermark to the result.',
+                    tooltip="Whether to add an AI-generated watermark to the result.",
+                    optional=True,
+                ),
+                IO.Combo.Input(
+                    "shot_type",
+                    options=["single", "multi"],
+                    tooltip="Specifies the shot type for the generated video, that is, whether the video is a "
+                    "single continuous shot or multiple shots with cuts. "
+                    "This parameter takes effect only when prompt_extend is True.",
                     optional=True,
                 ),
             ],
@@ -643,19 +665,24 @@ class WanImageToVideoApi(IO.ComfyNode):
     async def execute(
         cls,
         model: str,
-        image: torch.Tensor,
+        image: Input.Image,
         prompt: str,
         negative_prompt: str = "",
-        resolution: str = "480P",
+        resolution: str = "720P",
         duration: int = 5,
-        audio: Optional[Input.Audio] = None,
+        audio: Input.Audio | None = None,
         seed: int = 0,
         generate_audio: bool = False,
         prompt_extend: bool = True,
         watermark: bool = True,
+        shot_type: str = "single",
     ):
         if get_number_of_images(image) != 1:
             raise ValueError("Exactly one input image is required.")
+        if "480P" in resolution and model == "wan2.6-i2v":
+            raise ValueError("The Wan 2.6 model does not support 480P.")
+        if duration == 15 and model == "wan2.5-i2v-preview":
+            raise ValueError("A 15-second duration is supported only by the Wan 2.6 model.")
         image_url = "data:image/png;base64," + tensor_to_base64_string(image, total_pixels=2000 * 2000)
         audio_url = None
         if audio is not None:
@@ -677,11 +704,12 @@ class WanImageToVideoApi(IO.ComfyNode):
                     audio=generate_audio,
                     prompt_extend=prompt_extend,
                     watermark=watermark,
+                    shot_type=shot_type,
                 ),
             ),
         )
         if not initial_response.output:
-            raise Exception(f"Unknown error occurred: {initial_response.code} - {initial_response.message}")
+            raise Exception(f"An unknown error occurred: {initial_response.code} - {initial_response.message}")
         response = await poll_op(
             cls,
             ApiEndpoint(path=f"/proxy/wan/api/v1/tasks/{initial_response.output.task_id}"),

comfy_api_nodes/util/conversions.py

@@ -129,7 +129,7 @@ def pil_to_bytesio(img: Image.Image, mime_type: str = "image/png") -> BytesIO:
     return img_byte_arr
 
 
-def downscale_image_tensor(image, total_pixels=1536 * 1024) -> torch.Tensor:
+def downscale_image_tensor(image: torch.Tensor, total_pixels: int = 1536 * 1024) -> torch.Tensor:
     """Downscale input image tensor to roughly the specified total pixels."""
     samples = image.movedim(-1, 1)
     total = int(total_pixels)

comfy_extras/nodes_custom_sampler.py

@@ -671,7 +671,16 @@ class SamplerSEEDS2(io.ComfyNode):
                 io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, tooltip="SDE noise multiplier"),
                 io.Float.Input("r", default=0.5, min=0.01, max=1.0, step=0.01, round=False, tooltip="Relative step size for the intermediate stage (c2 node)"),
             ],
-            outputs=[io.Sampler.Output()]
+            outputs=[io.Sampler.Output()],
+            description=(
+                "This sampler node can represent multiple samplers:\n\n"
+                "seeds_2\n"
+                "- default setting\n\n"
+                "exp_heun_2_x0\n"
+                "- solver_type=phi_2, r=1.0, eta=0.0\n\n"
+                "exp_heun_2_x0_sde\n"
+                "- solver_type=phi_2, r=1.0, eta=1.0, s_noise=1.0"
+            )
         )
 
     @classmethod

comfy_extras/nodes_model_patch.py

@@ -248,7 +248,10 @@ class ModelPatchLoader:
                 config['n_control_layers'] = 15
                 config['additional_in_dim'] = 17
                 config['refiner_control'] = True
-                config['broken'] = True
+                ref_weight = sd.get("control_noise_refiner.0.after_proj.weight", None)
+                if ref_weight is not None:
+                    if torch.count_nonzero(ref_weight) == 0:
+                        config['broken'] = True
             model = comfy.ldm.lumina.controlnet.ZImage_Control(device=comfy.model_management.unet_offload_device(), dtype=dtype, operations=comfy.ops.manual_cast, **config)
 
         model.load_state_dict(sd)
@@ -310,22 +313,46 @@ class ZImageControlPatch:
         self.inpaint_image = inpaint_image
         self.mask = mask
         self.strength = strength
-        self.encoded_image = self.encode_latent_cond(image)
-        self.encoded_image_size = (image.shape[1], image.shape[2])
+        self.is_inpaint = self.model_patch.model.additional_in_dim > 0
+
+        skip_encoding = False
+        if self.image is not None and self.inpaint_image is not None:
+            if self.image.shape != self.inpaint_image.shape:
+                skip_encoding = True
+
+        if skip_encoding:
+            self.encoded_image = None
+        else:
+            self.encoded_image = self.encode_latent_cond(self.image, self.inpaint_image)
+            if self.image is None:
+                self.encoded_image_size = (self.inpaint_image.shape[1], self.inpaint_image.shape[2])
+            else:
+                self.encoded_image_size = (self.image.shape[1], self.image.shape[2])
         self.temp_data = None
 
-    def encode_latent_cond(self, control_image, inpaint_image=None):
-        latent_image = comfy.latent_formats.Flux().process_in(self.vae.encode(control_image))
-        if self.model_patch.model.additional_in_dim > 0:
-            if self.mask is None:
-                mask_ = torch.zeros_like(latent_image)[:, :1]
-            else:
-                mask_ = comfy.utils.common_upscale(self.mask.mean(dim=1, keepdim=True), latent_image.shape[-1], latent_image.shape[-2], "bilinear", "none")
+    def encode_latent_cond(self, control_image=None, inpaint_image=None):
+        latent_image = None
+        if control_image is not None:
+            latent_image = comfy.latent_formats.Flux().process_in(self.vae.encode(control_image))
+
+        if self.is_inpaint:
             if inpaint_image is None:
                 inpaint_image = torch.ones_like(control_image) * 0.5
 
+            if self.mask is not None:
+                mask_inpaint = comfy.utils.common_upscale(self.mask.view(self.mask.shape[0], -1, self.mask.shape[-2], self.mask.shape[-1]).mean(dim=1, keepdim=True), inpaint_image.shape[-2], inpaint_image.shape[-3], "bilinear", "center")
+                inpaint_image = ((inpaint_image - 0.5) * mask_inpaint.movedim(1, -1).round()) + 0.5
+
             inpaint_image_latent = comfy.latent_formats.Flux().process_in(self.vae.encode(inpaint_image))
 
+            if self.mask is None:
+                mask_ = torch.zeros_like(inpaint_image_latent)[:, :1]
+            else:
+                mask_ = comfy.utils.common_upscale(self.mask.view(self.mask.shape[0], -1, self.mask.shape[-2], self.mask.shape[-1]).mean(dim=1, keepdim=True), inpaint_image_latent.shape[-1], inpaint_image_latent.shape[-2], "nearest", "center")
+
+            if latent_image is None:
+                latent_image = comfy.latent_formats.Flux().process_in(self.vae.encode(torch.ones_like(inpaint_image) * 0.5))
+
             return torch.cat([latent_image, mask_, inpaint_image_latent], dim=1)
         else:
             return latent_image
@@ -341,13 +368,18 @@ class ZImageControlPatch:
         block_type = kwargs.get("block_type", "")
         spacial_compression = self.vae.spacial_compression_encode()
         if self.encoded_image is None or self.encoded_image_size != (x.shape[-2] * spacial_compression, x.shape[-1] * spacial_compression):
-            image_scaled = comfy.utils.common_upscale(self.image.movedim(-1, 1), x.shape[-1] * spacial_compression, x.shape[-2] * spacial_compression, "area", "center")
+            image_scaled = None
+            if self.image is not None:
+                image_scaled = comfy.utils.common_upscale(self.image.movedim(-1, 1), x.shape[-1] * spacial_compression, x.shape[-2] * spacial_compression, "area", "center").movedim(1, -1)
+                self.encoded_image_size = (image_scaled.shape[-3], image_scaled.shape[-2])
+
             inpaint_scaled = None
             if self.inpaint_image is not None:
                 inpaint_scaled = comfy.utils.common_upscale(self.inpaint_image.movedim(-1, 1), x.shape[-1] * spacial_compression, x.shape[-2] * spacial_compression, "area", "center").movedim(1, -1)
+                self.encoded_image_size = (inpaint_scaled.shape[-3], inpaint_scaled.shape[-2])
+
             loaded_models = comfy.model_management.loaded_models(only_currently_used=True)
-            self.encoded_image = self.encode_latent_cond(image_scaled.movedim(1, -1), inpaint_scaled)
-            self.encoded_image_size = (image_scaled.shape[-2], image_scaled.shape[-1])
+            self.encoded_image = self.encode_latent_cond(image_scaled, inpaint_scaled)
             comfy.model_management.load_models_gpu(loaded_models)
 
         cnet_blocks = self.model_patch.model.n_control_layers
@@ -388,7 +420,8 @@ class ZImageControlPatch:
 
     def to(self, device_or_dtype):
         if isinstance(device_or_dtype, torch.device):
-            self.encoded_image = self.encoded_image.to(device_or_dtype)
+            if self.encoded_image is not None:
+                self.encoded_image = self.encoded_image.to(device_or_dtype)
             self.temp_data = None
         return self
 
@@ -411,9 +444,12 @@ class QwenImageDiffsynthControlnet:
 
     CATEGORY = "advanced/loaders/qwen"
 
-    def diffsynth_controlnet(self, model, model_patch, vae, image, strength, mask=None):
+    def diffsynth_controlnet(self, model, model_patch, vae, image=None, strength=1.0, inpaint_image=None, mask=None):
         model_patched = model.clone()
-        image = image[:, :, :, :3]
+        if image is not None:
+            image = image[:, :, :, :3]
+        if inpaint_image is not None:
+            inpaint_image = inpaint_image[:, :, :, :3]
         if mask is not None:
             if mask.ndim == 3:
                 mask = mask.unsqueeze(1)
@@ -422,13 +458,24 @@ class QwenImageDiffsynthControlnet:
             mask = 1.0 - mask
 
         if isinstance(model_patch.model, comfy.ldm.lumina.controlnet.ZImage_Control):
-            patch = ZImageControlPatch(model_patch, vae, image, strength, mask=mask)
+            patch = ZImageControlPatch(model_patch, vae, image, strength, inpaint_image=inpaint_image, mask=mask)
             model_patched.set_model_noise_refiner_patch(patch)
             model_patched.set_model_double_block_patch(patch)
         else:
             model_patched.set_model_double_block_patch(DiffSynthCnetPatch(model_patch, vae, image, strength, mask))
         return (model_patched,)
 
+class ZImageFunControlnet(QwenImageDiffsynthControlnet):
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "model": ("MODEL",),
+                              "model_patch": ("MODEL_PATCH",),
+                              "vae": ("VAE",),
+                              "strength": ("FLOAT", {"default": 1.0, "min": -10.0, "max": 10.0, "step": 0.01}),
+                              },
+                "optional": {"image": ("IMAGE",), "inpaint_image": ("IMAGE",), "mask": ("MASK",)}}
+
+    CATEGORY = "advanced/loaders/zimage"
 
 class UsoStyleProjectorPatch:
     def __init__(self, model_patch, encoded_image):
@@ -476,5 +523,6 @@ class USOStyleReference:
 NODE_CLASS_MAPPINGS = {
     "ModelPatchLoader": ModelPatchLoader,
     "QwenImageDiffsynthControlnet": QwenImageDiffsynthControlnet,
+    "ZImageFunControlnet": ZImageFunControlnet,
     "USOStyleReference": USOStyleReference,
 }

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.4.0"
+__version__ = "0.5.1"

main.py

@@ -23,6 +23,38 @@ if __name__ == "__main__":
 
 setup_logger(log_level=args.verbose, use_stdout=args.log_stdout)
 
+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))
+        devices.remove(default_dev)
+        devices.insert(0, default_dev)
+        devices = ','.join(map(str, devices))
+        os.environ['CUDA_VISIBLE_DEVICES'] = str(devices)
+        os.environ['HIP_VISIBLE_DEVICES'] = str(devices)
+
+    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:
+        os.environ['ONEAPI_DEVICE_SELECTOR'] = args.oneapi_device_selector
+        logging.info("Set oneapi device selector to: {}".format(args.oneapi_device_selector))
+
+    if args.deterministic:
+        if 'CUBLAS_WORKSPACE_CONFIG' not in os.environ:
+            os.environ['CUBLAS_WORKSPACE_CONFIG'] = ":4096:8"
+
+    import cuda_malloc
+    if "rocm" in cuda_malloc.get_torch_version_noimport():
+        os.environ['OCL_SET_SVM_SIZE'] = '262144'  # set at the request of AMD
+
 
 def handle_comfyui_manager_unavailable():
     if not args.windows_standalone_build:
@@ -137,40 +169,6 @@ import shutil
 import threading
 import gc
 
-
-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))
-        devices.remove(default_dev)
-        devices.insert(0, default_dev)
-        devices = ','.join(map(str, devices))
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(devices)
-        os.environ['HIP_VISIBLE_DEVICES'] = str(devices)
-
-    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:
-        os.environ['ONEAPI_DEVICE_SELECTOR'] = args.oneapi_device_selector
-        logging.info("Set oneapi device selector to: {}".format(args.oneapi_device_selector))
-
-    if args.deterministic:
-        if 'CUBLAS_WORKSPACE_CONFIG' not in os.environ:
-            os.environ['CUBLAS_WORKSPACE_CONFIG'] = ":4096:8"
-
-    import cuda_malloc
-    if "rocm" in cuda_malloc.get_torch_version_noimport():
-        os.environ['OCL_SET_SVM_SIZE'] = '262144'  # set at the request of AMD
-
-
 if 'torch' in sys.modules:
     logging.warning("WARNING: Potential Error in code: Torch already imported, torch should never be imported before this point.")
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.4.0"
+version = "0.5.1"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"

requirements.txt

@@ -1,4 +1,4 @@
-comfyui-frontend-package==1.34.8
+comfyui-frontend-package==1.34.9
 comfyui-workflow-templates==0.7.59
 comfyui-embedded-docs==0.3.1
 torch