mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-04-09 05:59:56 +00:00
Compare commits
1 Commits
feat/api-n
...
dev/Combo-
| Author | SHA1 | Date | |
|---|---|---|---|
|
d25d14dfb6 |
36
.github/workflows/release-stable-all.yml
vendored
36
.github/workflows/release-stable-all.yml
vendored
@@ -20,12 +20,29 @@ jobs:
|
||||
git_tag: ${{ inputs.git_tag }}
|
||||
cache_tag: "cu130"
|
||||
python_minor: "13"
|
||||
python_patch: "12"
|
||||
python_patch: "11"
|
||||
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_nvidia_cu126:
|
||||
permissions:
|
||||
contents: "write"
|
||||
@@ -59,20 +76,3 @@ jobs:
|
||||
rel_extra_name: ""
|
||||
test_release: false
|
||||
secrets: inherit
|
||||
|
||||
release_xpu:
|
||||
permissions:
|
||||
contents: "write"
|
||||
packages: "write"
|
||||
pull-requests: "read"
|
||||
name: "Release Intel XPU"
|
||||
uses: ./.github/workflows/stable-release.yml
|
||||
with:
|
||||
git_tag: ${{ inputs.git_tag }}
|
||||
cache_tag: "xpu"
|
||||
python_minor: "13"
|
||||
python_patch: "12"
|
||||
rel_name: "intel"
|
||||
rel_extra_name: ""
|
||||
test_release: true
|
||||
secrets: inherit
|
||||
|
||||
@@ -61,7 +61,6 @@ See what ComfyUI can do with the [newer template workflows](https://comfy.org/wo
|
||||
|
||||
## Features
|
||||
- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
|
||||
- NOTE: There are many more models supported than the list below, if you want to see what is supported see our templates list inside ComfyUI.
|
||||
- Image Models
|
||||
- SD1.x, SD2.x ([unCLIP](https://comfyanonymous.github.io/ComfyUI_examples/unclip/))
|
||||
- [SDXL](https://comfyanonymous.github.io/ComfyUI_examples/sdxl/), [SDXL Turbo](https://comfyanonymous.github.io/ComfyUI_examples/sdturbo/)
|
||||
@@ -137,7 +136,7 @@ ComfyUI follows a weekly release cycle targeting Monday but this regularly chang
|
||||
- Builds a new release using the latest stable core version
|
||||
|
||||
3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)**
|
||||
- Every 2+ weeks frontend updates are merged into the core repository
|
||||
- Weekly frontend updates are merged into the core repository
|
||||
- Features are frozen for the upcoming core release
|
||||
- Development continues for the next release cycle
|
||||
|
||||
@@ -276,7 +275,7 @@ 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/cu132```
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130```
|
||||
|
||||
#### Troubleshooting
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,322 +1 @@
|
||||
{
|
||||
"revision": 0,
|
||||
"last_node_id": 29,
|
||||
"last_link_id": 0,
|
||||
"nodes": [
|
||||
{
|
||||
"id": 29,
|
||||
"type": "4c9d6ea4-b912-40e5-8766-6793a9758c53",
|
||||
"pos": [
|
||||
1970,
|
||||
-230
|
||||
],
|
||||
"size": [
|
||||
180,
|
||||
86
|
||||
],
|
||||
"flags": {},
|
||||
"order": 5,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"label": "image",
|
||||
"localized_name": "images.image0",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"label": "R",
|
||||
"localized_name": "IMAGE0",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"links": []
|
||||
},
|
||||
{
|
||||
"label": "G",
|
||||
"localized_name": "IMAGE1",
|
||||
"name": "IMAGE1",
|
||||
"type": "IMAGE",
|
||||
"links": []
|
||||
},
|
||||
{
|
||||
"label": "B",
|
||||
"localized_name": "IMAGE2",
|
||||
"name": "IMAGE2",
|
||||
"type": "IMAGE",
|
||||
"links": []
|
||||
},
|
||||
{
|
||||
"label": "A",
|
||||
"localized_name": "IMAGE3",
|
||||
"name": "IMAGE3",
|
||||
"type": "IMAGE",
|
||||
"links": []
|
||||
}
|
||||
],
|
||||
"title": "Image Channels",
|
||||
"properties": {
|
||||
"proxyWidgets": []
|
||||
},
|
||||
"widgets_values": []
|
||||
}
|
||||
],
|
||||
"links": [],
|
||||
"version": 0.4,
|
||||
"definitions": {
|
||||
"subgraphs": [
|
||||
{
|
||||
"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53",
|
||||
"version": 1,
|
||||
"state": {
|
||||
"lastGroupId": 0,
|
||||
"lastNodeId": 28,
|
||||
"lastLinkId": 39,
|
||||
"lastRerouteId": 0
|
||||
},
|
||||
"revision": 0,
|
||||
"config": {},
|
||||
"name": "Image Channels",
|
||||
"inputNode": {
|
||||
"id": -10,
|
||||
"bounding": [
|
||||
1820,
|
||||
-185,
|
||||
120,
|
||||
60
|
||||
]
|
||||
},
|
||||
"outputNode": {
|
||||
"id": -20,
|
||||
"bounding": [
|
||||
2460,
|
||||
-215,
|
||||
120,
|
||||
120
|
||||
]
|
||||
},
|
||||
"inputs": [
|
||||
{
|
||||
"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
39
|
||||
],
|
||||
"localized_name": "images.image0",
|
||||
"label": "image",
|
||||
"pos": [
|
||||
1920,
|
||||
-165
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
26
|
||||
],
|
||||
"localized_name": "IMAGE0",
|
||||
"label": "R",
|
||||
"pos": [
|
||||
2480,
|
||||
-195
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "fb44a77e-0522-43e9-9527-82e7465b3596",
|
||||
"name": "IMAGE1",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
27
|
||||
],
|
||||
"localized_name": "IMAGE1",
|
||||
"label": "G",
|
||||
"pos": [
|
||||
2480,
|
||||
-175
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "81460ee6-0131-402a-874f-6bf3001fc4ff",
|
||||
"name": "IMAGE2",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
28
|
||||
],
|
||||
"localized_name": "IMAGE2",
|
||||
"label": "B",
|
||||
"pos": [
|
||||
2480,
|
||||
-155
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "ae690246-80d4-4951-b1d9-9306d8a77417",
|
||||
"name": "IMAGE3",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
29
|
||||
],
|
||||
"localized_name": "IMAGE3",
|
||||
"label": "A",
|
||||
"pos": [
|
||||
2480,
|
||||
-135
|
||||
]
|
||||
}
|
||||
],
|
||||
"widgets": [],
|
||||
"nodes": [
|
||||
{
|
||||
"id": 23,
|
||||
"type": "GLSLShader",
|
||||
"pos": [
|
||||
2000,
|
||||
-330
|
||||
],
|
||||
"size": [
|
||||
400,
|
||||
172
|
||||
],
|
||||
"flags": {},
|
||||
"order": 0,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"label": "image",
|
||||
"localized_name": "images.image0",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"link": 39
|
||||
},
|
||||
{
|
||||
"localized_name": "fragment_shader",
|
||||
"name": "fragment_shader",
|
||||
"type": "STRING",
|
||||
"widget": {
|
||||
"name": "fragment_shader"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "size_mode",
|
||||
"name": "size_mode",
|
||||
"type": "COMFY_DYNAMICCOMBO_V3",
|
||||
"widget": {
|
||||
"name": "size_mode"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"label": "image1",
|
||||
"localized_name": "images.image1",
|
||||
"name": "images.image1",
|
||||
"shape": 7,
|
||||
"type": "IMAGE",
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"label": "R",
|
||||
"localized_name": "IMAGE0",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
26
|
||||
]
|
||||
},
|
||||
{
|
||||
"label": "G",
|
||||
"localized_name": "IMAGE1",
|
||||
"name": "IMAGE1",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
27
|
||||
]
|
||||
},
|
||||
{
|
||||
"label": "B",
|
||||
"localized_name": "IMAGE2",
|
||||
"name": "IMAGE2",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
28
|
||||
]
|
||||
},
|
||||
{
|
||||
"label": "A",
|
||||
"localized_name": "IMAGE3",
|
||||
"name": "IMAGE3",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
29
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"Node name for S&R": "GLSLShader"
|
||||
},
|
||||
"widgets_values": [
|
||||
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n",
|
||||
"from_input"
|
||||
]
|
||||
}
|
||||
],
|
||||
"groups": [],
|
||||
"links": [
|
||||
{
|
||||
"id": 39,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 0,
|
||||
"target_id": 23,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 26,
|
||||
"origin_id": 23,
|
||||
"origin_slot": 0,
|
||||
"target_id": -20,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 27,
|
||||
"origin_id": 23,
|
||||
"origin_slot": 1,
|
||||
"target_id": -20,
|
||||
"target_slot": 1,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 28,
|
||||
"origin_id": 23,
|
||||
"origin_slot": 2,
|
||||
"target_id": -20,
|
||||
"target_slot": 2,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 29,
|
||||
"origin_id": 23,
|
||||
"origin_slot": 3,
|
||||
"target_id": -20,
|
||||
"target_slot": 3,
|
||||
"type": "IMAGE"
|
||||
}
|
||||
],
|
||||
"extra": {
|
||||
"workflowRendererVersion": "LG"
|
||||
},
|
||||
"category": "Image Tools/Color adjust"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
{"revision": 0, "last_node_id": 29, "last_link_id": 0, "nodes": [{"id": 29, "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "pos": [1970, -230], "size": [180, 86], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "title": "Image Channels", "properties": {"proxyWidgets": []}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 28, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Channels", "inputNode": {"id": -10, "bounding": [1820, -185, 120, 60]}, "outputNode": {"id": -20, "bounding": [2460, -215, 120, 120]}, "inputs": [{"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image", "pos": [1920, -165]}], "outputs": [{"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", "name": "IMAGE0", "type": "IMAGE", "linkIds": [26], "localized_name": "IMAGE0", "label": "R", "pos": [2480, -195]}, {"id": "fb44a77e-0522-43e9-9527-82e7465b3596", "name": "IMAGE1", "type": "IMAGE", "linkIds": [27], "localized_name": "IMAGE1", "label": "G", "pos": [2480, -175]}, {"id": "81460ee6-0131-402a-874f-6bf3001fc4ff", "name": "IMAGE2", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE2", "label": "B", "pos": [2480, -155]}, {"id": "ae690246-80d4-4951-b1d9-9306d8a77417", "name": "IMAGE3", "type": "IMAGE", "linkIds": [29], "localized_name": "IMAGE3", "label": "A", "pos": [2480, -135]}], "widgets": [], "nodes": [{"id": 23, "type": "GLSLShader", "pos": [2000, -330], "size": [400, 172], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [26]}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": [27]}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": [28]}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": [29]}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n", "from_input"]}], "groups": [], "links": [{"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 23, "origin_slot": 1, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 28, "origin_id": 23, "origin_slot": 2, "target_id": -20, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 23, "origin_slot": 3, "target_id": -20, "target_slot": 3, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}}
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,278 +1 @@
|
||||
{
|
||||
"revision": 0,
|
||||
"last_node_id": 15,
|
||||
"last_link_id": 0,
|
||||
"nodes": [
|
||||
{
|
||||
"id": 15,
|
||||
"type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471",
|
||||
"pos": [
|
||||
-1490,
|
||||
2040
|
||||
],
|
||||
"size": [
|
||||
400,
|
||||
260
|
||||
],
|
||||
"flags": {},
|
||||
"order": 0,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"name": "prompt",
|
||||
"type": "STRING",
|
||||
"widget": {
|
||||
"name": "prompt"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"label": "reference images",
|
||||
"name": "images",
|
||||
"type": "IMAGE",
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "STRING",
|
||||
"type": "STRING",
|
||||
"links": null
|
||||
}
|
||||
],
|
||||
"title": "Prompt Enhance",
|
||||
"properties": {
|
||||
"proxyWidgets": [
|
||||
[
|
||||
"-1",
|
||||
"prompt"
|
||||
]
|
||||
],
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.14.1"
|
||||
},
|
||||
"widgets_values": [
|
||||
""
|
||||
]
|
||||
}
|
||||
],
|
||||
"links": [],
|
||||
"version": 0.4,
|
||||
"definitions": {
|
||||
"subgraphs": [
|
||||
{
|
||||
"id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471",
|
||||
"version": 1,
|
||||
"state": {
|
||||
"lastGroupId": 0,
|
||||
"lastNodeId": 15,
|
||||
"lastLinkId": 14,
|
||||
"lastRerouteId": 0
|
||||
},
|
||||
"revision": 0,
|
||||
"config": {},
|
||||
"name": "Prompt Enhance",
|
||||
"inputNode": {
|
||||
"id": -10,
|
||||
"bounding": [
|
||||
-2170,
|
||||
2110,
|
||||
138.876953125,
|
||||
80
|
||||
]
|
||||
},
|
||||
"outputNode": {
|
||||
"id": -20,
|
||||
"bounding": [
|
||||
-640,
|
||||
2110,
|
||||
120,
|
||||
60
|
||||
]
|
||||
},
|
||||
"inputs": [
|
||||
{
|
||||
"id": "aeab7216-00e0-4528-a09b-bba50845c5a6",
|
||||
"name": "prompt",
|
||||
"type": "STRING",
|
||||
"linkIds": [
|
||||
11
|
||||
],
|
||||
"pos": [
|
||||
-2051.123046875,
|
||||
2130
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "7b73fd36-aa31-4771-9066-f6c83879994b",
|
||||
"name": "images",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
14
|
||||
],
|
||||
"label": "reference images",
|
||||
"pos": [
|
||||
-2051.123046875,
|
||||
2150
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"id": "c7b0d930-68a1-48d1-b496-0519e5837064",
|
||||
"name": "STRING",
|
||||
"type": "STRING",
|
||||
"linkIds": [
|
||||
13
|
||||
],
|
||||
"pos": [
|
||||
-620,
|
||||
2130
|
||||
]
|
||||
}
|
||||
],
|
||||
"widgets": [],
|
||||
"nodes": [
|
||||
{
|
||||
"id": 11,
|
||||
"type": "GeminiNode",
|
||||
"pos": [
|
||||
-1560,
|
||||
1990
|
||||
],
|
||||
"size": [
|
||||
470,
|
||||
470
|
||||
],
|
||||
"flags": {},
|
||||
"order": 0,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "images",
|
||||
"name": "images",
|
||||
"shape": 7,
|
||||
"type": "IMAGE",
|
||||
"link": 14
|
||||
},
|
||||
{
|
||||
"localized_name": "audio",
|
||||
"name": "audio",
|
||||
"shape": 7,
|
||||
"type": "AUDIO",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "video",
|
||||
"name": "video",
|
||||
"shape": 7,
|
||||
"type": "VIDEO",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "files",
|
||||
"name": "files",
|
||||
"shape": 7,
|
||||
"type": "GEMINI_INPUT_FILES",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "prompt",
|
||||
"name": "prompt",
|
||||
"type": "STRING",
|
||||
"widget": {
|
||||
"name": "prompt"
|
||||
},
|
||||
"link": 11
|
||||
},
|
||||
{
|
||||
"localized_name": "model",
|
||||
"name": "model",
|
||||
"type": "COMBO",
|
||||
"widget": {
|
||||
"name": "model"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "seed",
|
||||
"name": "seed",
|
||||
"type": "INT",
|
||||
"widget": {
|
||||
"name": "seed"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "system_prompt",
|
||||
"name": "system_prompt",
|
||||
"shape": 7,
|
||||
"type": "STRING",
|
||||
"widget": {
|
||||
"name": "system_prompt"
|
||||
},
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "STRING",
|
||||
"name": "STRING",
|
||||
"type": "STRING",
|
||||
"links": [
|
||||
13
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.14.1",
|
||||
"Node name for S&R": "GeminiNode"
|
||||
},
|
||||
"widgets_values": [
|
||||
"",
|
||||
"gemini-3-pro-preview",
|
||||
42,
|
||||
"randomize",
|
||||
"You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only"
|
||||
],
|
||||
"color": "#432",
|
||||
"bgcolor": "#653"
|
||||
}
|
||||
],
|
||||
"groups": [],
|
||||
"links": [
|
||||
{
|
||||
"id": 11,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 0,
|
||||
"target_id": 11,
|
||||
"target_slot": 4,
|
||||
"type": "STRING"
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"origin_id": 11,
|
||||
"origin_slot": 0,
|
||||
"target_id": -20,
|
||||
"target_slot": 0,
|
||||
"type": "STRING"
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 1,
|
||||
"target_id": 11,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
}
|
||||
],
|
||||
"extra": {
|
||||
"workflowRendererVersion": "LG"
|
||||
},
|
||||
"category": "Text generation/Prompt enhance"
|
||||
}
|
||||
]
|
||||
},
|
||||
"extra": {}
|
||||
}
|
||||
{"revision": 0, "last_node_id": 15, "last_link_id": 0, "nodes": [{"id": 15, "type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "pos": [-1490, 2040], "size": [400, 260], "flags": {}, "order": 0, "mode": 0, "inputs": [{"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"label": "reference images", "name": "images", "type": "IMAGE", "link": null}], "outputs": [{"name": "STRING", "type": "STRING", "links": null}], "title": "Prompt Enhance", "properties": {"proxyWidgets": [["-1", "prompt"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [""]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 15, "lastLinkId": 14, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Prompt Enhance", "inputNode": {"id": -10, "bounding": [-2170, 2110, 138.876953125, 80]}, "outputNode": {"id": -20, "bounding": [-640, 2110, 120, 60]}, "inputs": [{"id": "aeab7216-00e0-4528-a09b-bba50845c5a6", "name": "prompt", "type": "STRING", "linkIds": [11], "pos": [-2051.123046875, 2130]}, {"id": "7b73fd36-aa31-4771-9066-f6c83879994b", "name": "images", "type": "IMAGE", "linkIds": [14], "label": "reference images", "pos": [-2051.123046875, 2150]}], "outputs": [{"id": "c7b0d930-68a1-48d1-b496-0519e5837064", "name": "STRING", "type": "STRING", "linkIds": [13], "pos": [-620, 2130]}], "widgets": [], "nodes": [{"id": 11, "type": "GeminiNode", "pos": [-1560, 1990], "size": [470, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": 14}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": null}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 11}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.14.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["", "gemini-3-pro-preview", 42, "randomize", "You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only"], "color": "#432", "bgcolor": "#653"}], "groups": [], "links": [{"id": 11, "origin_id": -10, "origin_slot": 0, "target_id": 11, "target_slot": 4, "type": "STRING"}, {"id": 13, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "STRING"}, {"id": 14, "origin_id": -10, "origin_slot": 1, "target_id": 11, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Text generation/Prompt enhance"}]}, "extra": {}}
|
||||
|
||||
@@ -1,309 +1 @@
|
||||
{
|
||||
"revision": 0,
|
||||
"last_node_id": 25,
|
||||
"last_link_id": 0,
|
||||
"nodes": [
|
||||
{
|
||||
"id": 25,
|
||||
"type": "621ba4e2-22a8-482d-a369-023753198b7b",
|
||||
"pos": [
|
||||
4610,
|
||||
-790
|
||||
],
|
||||
"size": [
|
||||
230,
|
||||
58
|
||||
],
|
||||
"flags": {},
|
||||
"order": 4,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"label": "image",
|
||||
"localized_name": "images.image0",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"label": "IMAGE",
|
||||
"localized_name": "IMAGE0",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"links": []
|
||||
}
|
||||
],
|
||||
"title": "Sharpen",
|
||||
"properties": {
|
||||
"proxyWidgets": [
|
||||
[
|
||||
"24",
|
||||
"value"
|
||||
]
|
||||
]
|
||||
},
|
||||
"widgets_values": []
|
||||
}
|
||||
],
|
||||
"links": [],
|
||||
"version": 0.4,
|
||||
"definitions": {
|
||||
"subgraphs": [
|
||||
{
|
||||
"id": "621ba4e2-22a8-482d-a369-023753198b7b",
|
||||
"version": 1,
|
||||
"state": {
|
||||
"lastGroupId": 0,
|
||||
"lastNodeId": 24,
|
||||
"lastLinkId": 36,
|
||||
"lastRerouteId": 0
|
||||
},
|
||||
"revision": 0,
|
||||
"config": {},
|
||||
"name": "Sharpen",
|
||||
"inputNode": {
|
||||
"id": -10,
|
||||
"bounding": [
|
||||
4090,
|
||||
-825,
|
||||
120,
|
||||
60
|
||||
]
|
||||
},
|
||||
"outputNode": {
|
||||
"id": -20,
|
||||
"bounding": [
|
||||
5150,
|
||||
-825,
|
||||
120,
|
||||
60
|
||||
]
|
||||
},
|
||||
"inputs": [
|
||||
{
|
||||
"id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
34
|
||||
],
|
||||
"localized_name": "images.image0",
|
||||
"label": "image",
|
||||
"pos": [
|
||||
4190,
|
||||
-805
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"linkIds": [
|
||||
35
|
||||
],
|
||||
"localized_name": "IMAGE0",
|
||||
"label": "IMAGE",
|
||||
"pos": [
|
||||
5170,
|
||||
-805
|
||||
]
|
||||
}
|
||||
],
|
||||
"widgets": [],
|
||||
"nodes": [
|
||||
{
|
||||
"id": 24,
|
||||
"type": "PrimitiveFloat",
|
||||
"pos": [
|
||||
4280,
|
||||
-1240
|
||||
],
|
||||
"size": [
|
||||
270,
|
||||
58
|
||||
],
|
||||
"flags": {},
|
||||
"order": 0,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"label": "strength",
|
||||
"localized_name": "value",
|
||||
"name": "value",
|
||||
"type": "FLOAT",
|
||||
"widget": {
|
||||
"name": "value"
|
||||
},
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "FLOAT",
|
||||
"name": "FLOAT",
|
||||
"type": "FLOAT",
|
||||
"links": [
|
||||
36
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"Node name for S&R": "PrimitiveFloat",
|
||||
"min": 0,
|
||||
"max": 3,
|
||||
"precision": 2,
|
||||
"step": 0.05
|
||||
},
|
||||
"widgets_values": [
|
||||
0.5
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 23,
|
||||
"type": "GLSLShader",
|
||||
"pos": [
|
||||
4570,
|
||||
-1240
|
||||
],
|
||||
"size": [
|
||||
370,
|
||||
192
|
||||
],
|
||||
"flags": {},
|
||||
"order": 1,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"label": "image0",
|
||||
"localized_name": "images.image0",
|
||||
"name": "images.image0",
|
||||
"type": "IMAGE",
|
||||
"link": 34
|
||||
},
|
||||
{
|
||||
"label": "image1",
|
||||
"localized_name": "images.image1",
|
||||
"name": "images.image1",
|
||||
"shape": 7,
|
||||
"type": "IMAGE",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"label": "u_float0",
|
||||
"localized_name": "floats.u_float0",
|
||||
"name": "floats.u_float0",
|
||||
"shape": 7,
|
||||
"type": "FLOAT",
|
||||
"link": 36
|
||||
},
|
||||
{
|
||||
"label": "u_float1",
|
||||
"localized_name": "floats.u_float1",
|
||||
"name": "floats.u_float1",
|
||||
"shape": 7,
|
||||
"type": "FLOAT",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"label": "u_int0",
|
||||
"localized_name": "ints.u_int0",
|
||||
"name": "ints.u_int0",
|
||||
"shape": 7,
|
||||
"type": "INT",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "fragment_shader",
|
||||
"name": "fragment_shader",
|
||||
"type": "STRING",
|
||||
"widget": {
|
||||
"name": "fragment_shader"
|
||||
},
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"localized_name": "size_mode",
|
||||
"name": "size_mode",
|
||||
"type": "COMFY_DYNAMICCOMBO_V3",
|
||||
"widget": {
|
||||
"name": "size_mode"
|
||||
},
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "IMAGE0",
|
||||
"name": "IMAGE0",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
35
|
||||
]
|
||||
},
|
||||
{
|
||||
"localized_name": "IMAGE1",
|
||||
"name": "IMAGE1",
|
||||
"type": "IMAGE",
|
||||
"links": null
|
||||
},
|
||||
{
|
||||
"localized_name": "IMAGE2",
|
||||
"name": "IMAGE2",
|
||||
"type": "IMAGE",
|
||||
"links": null
|
||||
},
|
||||
{
|
||||
"localized_name": "IMAGE3",
|
||||
"name": "IMAGE3",
|
||||
"type": "IMAGE",
|
||||
"links": null
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"Node name for S&R": "GLSLShader"
|
||||
},
|
||||
"widgets_values": [
|
||||
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 – 2.0] typical: 0.3–1.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}",
|
||||
"from_input"
|
||||
]
|
||||
}
|
||||
],
|
||||
"groups": [],
|
||||
"links": [
|
||||
{
|
||||
"id": 36,
|
||||
"origin_id": 24,
|
||||
"origin_slot": 0,
|
||||
"target_id": 23,
|
||||
"target_slot": 2,
|
||||
"type": "FLOAT"
|
||||
},
|
||||
{
|
||||
"id": 34,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 0,
|
||||
"target_id": 23,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 35,
|
||||
"origin_id": 23,
|
||||
"origin_slot": 0,
|
||||
"target_id": -20,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
}
|
||||
],
|
||||
"extra": {
|
||||
"workflowRendererVersion": "LG"
|
||||
},
|
||||
"category": "Image Tools/Sharpen"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
{"revision": 0, "last_node_id": 25, "last_link_id": 0, "nodes": [{"id": 25, "type": "621ba4e2-22a8-482d-a369-023753198b7b", "pos": [4610, -790], "size": [230, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Sharpen", "properties": {"proxyWidgets": [["24", "value"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "621ba4e2-22a8-482d-a369-023753198b7b", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 24, "lastLinkId": 36, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Sharpen", "inputNode": {"id": -10, "bounding": [4090, -825, 120, 60]}, "outputNode": {"id": -20, "bounding": [5150, -825, 120, 60]}, "inputs": [{"id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7", "name": "images.image0", "type": "IMAGE", "linkIds": [34], "localized_name": "images.image0", "label": "image", "pos": [4190, -805]}], "outputs": [{"id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9", "name": "IMAGE0", "type": "IMAGE", "linkIds": [35], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [5170, -805]}], "widgets": [], "nodes": [{"id": 24, "type": "PrimitiveFloat", "pos": [4280, -1240], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "strength", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [36]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 3, "precision": 2, "step": 0.05}, "widgets_values": [0.5]}, {"id": 23, "type": "GLSLShader", "pos": [4570, -1240], "size": [370, 192], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 34}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 36}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [35]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 – 2.0] typical: 0.3–1.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}", "from_input"]}], "groups": [], "links": [{"id": 36, "origin_id": 24, "origin_slot": 0, "target_id": 23, "target_slot": 2, "type": "FLOAT"}, {"id": 34, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 35, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Sharpen"}]}}
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,420 +1 @@
|
||||
{
|
||||
"revision": 0,
|
||||
"last_node_id": 13,
|
||||
"last_link_id": 0,
|
||||
"nodes": [
|
||||
{
|
||||
"id": 13,
|
||||
"type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1",
|
||||
"pos": [
|
||||
1120,
|
||||
330
|
||||
],
|
||||
"size": [
|
||||
240,
|
||||
58
|
||||
],
|
||||
"flags": {},
|
||||
"order": 3,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "video",
|
||||
"name": "video",
|
||||
"type": "VIDEO",
|
||||
"link": null
|
||||
},
|
||||
{
|
||||
"name": "model_name",
|
||||
"type": "COMBO",
|
||||
"widget": {
|
||||
"name": "model_name"
|
||||
},
|
||||
"link": null
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "VIDEO",
|
||||
"name": "VIDEO",
|
||||
"type": "VIDEO",
|
||||
"links": []
|
||||
}
|
||||
],
|
||||
"title": "Video Upscale(GAN x4)",
|
||||
"properties": {
|
||||
"proxyWidgets": [
|
||||
[
|
||||
"-1",
|
||||
"model_name"
|
||||
]
|
||||
],
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.14.1"
|
||||
},
|
||||
"widgets_values": [
|
||||
"RealESRGAN_x4plus.safetensors"
|
||||
]
|
||||
}
|
||||
],
|
||||
"links": [],
|
||||
"version": 0.4,
|
||||
"definitions": {
|
||||
"subgraphs": [
|
||||
{
|
||||
"id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1",
|
||||
"version": 1,
|
||||
"state": {
|
||||
"lastGroupId": 0,
|
||||
"lastNodeId": 13,
|
||||
"lastLinkId": 19,
|
||||
"lastRerouteId": 0
|
||||
},
|
||||
"revision": 0,
|
||||
"config": {},
|
||||
"name": "Video Upscale(GAN x4)",
|
||||
"inputNode": {
|
||||
"id": -10,
|
||||
"bounding": [
|
||||
550,
|
||||
460,
|
||||
120,
|
||||
80
|
||||
]
|
||||
},
|
||||
"outputNode": {
|
||||
"id": -20,
|
||||
"bounding": [
|
||||
1490,
|
||||
460,
|
||||
120,
|
||||
60
|
||||
]
|
||||
},
|
||||
"inputs": [
|
||||
{
|
||||
"id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6",
|
||||
"name": "video",
|
||||
"type": "VIDEO",
|
||||
"linkIds": [
|
||||
10
|
||||
],
|
||||
"localized_name": "video",
|
||||
"pos": [
|
||||
650,
|
||||
480
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "2e23a087-caa8-4d65-99e6-662761aa905a",
|
||||
"name": "model_name",
|
||||
"type": "COMBO",
|
||||
"linkIds": [
|
||||
19
|
||||
],
|
||||
"pos": [
|
||||
650,
|
||||
500
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70",
|
||||
"name": "VIDEO",
|
||||
"type": "VIDEO",
|
||||
"linkIds": [
|
||||
15
|
||||
],
|
||||
"localized_name": "VIDEO",
|
||||
"pos": [
|
||||
1510,
|
||||
480
|
||||
]
|
||||
}
|
||||
],
|
||||
"widgets": [],
|
||||
"nodes": [
|
||||
{
|
||||
"id": 2,
|
||||
"type": "ImageUpscaleWithModel",
|
||||
"pos": [
|
||||
1110,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
320,
|
||||
46
|
||||
],
|
||||
"flags": {},
|
||||
"order": 1,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "upscale_model",
|
||||
"name": "upscale_model",
|
||||
"type": "UPSCALE_MODEL",
|
||||
"link": 1
|
||||
},
|
||||
{
|
||||
"localized_name": "image",
|
||||
"name": "image",
|
||||
"type": "IMAGE",
|
||||
"link": 14
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "IMAGE",
|
||||
"name": "IMAGE",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
13
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.10.0",
|
||||
"Node name for S&R": "ImageUpscaleWithModel"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"type": "CreateVideo",
|
||||
"pos": [
|
||||
1110,
|
||||
550
|
||||
],
|
||||
"size": [
|
||||
320,
|
||||
78
|
||||
],
|
||||
"flags": {},
|
||||
"order": 3,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "images",
|
||||
"name": "images",
|
||||
"type": "IMAGE",
|
||||
"link": 13
|
||||
},
|
||||
{
|
||||
"localized_name": "audio",
|
||||
"name": "audio",
|
||||
"shape": 7,
|
||||
"type": "AUDIO",
|
||||
"link": 16
|
||||
},
|
||||
{
|
||||
"localized_name": "fps",
|
||||
"name": "fps",
|
||||
"type": "FLOAT",
|
||||
"widget": {
|
||||
"name": "fps"
|
||||
},
|
||||
"link": 12
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "VIDEO",
|
||||
"name": "VIDEO",
|
||||
"type": "VIDEO",
|
||||
"links": [
|
||||
15
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.10.0",
|
||||
"Node name for S&R": "CreateVideo"
|
||||
},
|
||||
"widgets_values": [
|
||||
30
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"type": "GetVideoComponents",
|
||||
"pos": [
|
||||
1110,
|
||||
330
|
||||
],
|
||||
"size": [
|
||||
320,
|
||||
70
|
||||
],
|
||||
"flags": {},
|
||||
"order": 2,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "video",
|
||||
"name": "video",
|
||||
"type": "VIDEO",
|
||||
"link": 10
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "images",
|
||||
"name": "images",
|
||||
"type": "IMAGE",
|
||||
"links": [
|
||||
14
|
||||
]
|
||||
},
|
||||
{
|
||||
"localized_name": "audio",
|
||||
"name": "audio",
|
||||
"type": "AUDIO",
|
||||
"links": [
|
||||
16
|
||||
]
|
||||
},
|
||||
{
|
||||
"localized_name": "fps",
|
||||
"name": "fps",
|
||||
"type": "FLOAT",
|
||||
"links": [
|
||||
12
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.10.0",
|
||||
"Node name for S&R": "GetVideoComponents"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"type": "UpscaleModelLoader",
|
||||
"pos": [
|
||||
750,
|
||||
450
|
||||
],
|
||||
"size": [
|
||||
280,
|
||||
60
|
||||
],
|
||||
"flags": {},
|
||||
"order": 0,
|
||||
"mode": 0,
|
||||
"inputs": [
|
||||
{
|
||||
"localized_name": "model_name",
|
||||
"name": "model_name",
|
||||
"type": "COMBO",
|
||||
"widget": {
|
||||
"name": "model_name"
|
||||
},
|
||||
"link": 19
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"localized_name": "UPSCALE_MODEL",
|
||||
"name": "UPSCALE_MODEL",
|
||||
"type": "UPSCALE_MODEL",
|
||||
"links": [
|
||||
1
|
||||
]
|
||||
}
|
||||
],
|
||||
"properties": {
|
||||
"cnr_id": "comfy-core",
|
||||
"ver": "0.10.0",
|
||||
"Node name for S&R": "UpscaleModelLoader",
|
||||
"models": [
|
||||
{
|
||||
"name": "RealESRGAN_x4plus.safetensors",
|
||||
"url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors",
|
||||
"directory": "upscale_models"
|
||||
}
|
||||
]
|
||||
},
|
||||
"widgets_values": [
|
||||
"RealESRGAN_x4plus.safetensors"
|
||||
]
|
||||
}
|
||||
],
|
||||
"groups": [],
|
||||
"links": [
|
||||
{
|
||||
"id": 1,
|
||||
"origin_id": 1,
|
||||
"origin_slot": 0,
|
||||
"target_id": 2,
|
||||
"target_slot": 0,
|
||||
"type": "UPSCALE_MODEL"
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"origin_id": 10,
|
||||
"origin_slot": 0,
|
||||
"target_id": 2,
|
||||
"target_slot": 1,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"origin_id": 2,
|
||||
"origin_slot": 0,
|
||||
"target_id": 11,
|
||||
"target_slot": 0,
|
||||
"type": "IMAGE"
|
||||
},
|
||||
{
|
||||
"id": 16,
|
||||
"origin_id": 10,
|
||||
"origin_slot": 1,
|
||||
"target_id": 11,
|
||||
"target_slot": 1,
|
||||
"type": "AUDIO"
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"origin_id": 10,
|
||||
"origin_slot": 2,
|
||||
"target_id": 11,
|
||||
"target_slot": 2,
|
||||
"type": "FLOAT"
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 0,
|
||||
"target_id": 10,
|
||||
"target_slot": 0,
|
||||
"type": "VIDEO"
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"origin_id": 11,
|
||||
"origin_slot": 0,
|
||||
"target_id": -20,
|
||||
"target_slot": 0,
|
||||
"type": "VIDEO"
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"origin_id": -10,
|
||||
"origin_slot": 1,
|
||||
"target_id": 1,
|
||||
"target_slot": 0,
|
||||
"type": "COMBO"
|
||||
}
|
||||
],
|
||||
"extra": {
|
||||
"workflowRendererVersion": "LG"
|
||||
},
|
||||
"category": "Video generation and editing/Enhance video"
|
||||
}
|
||||
]
|
||||
},
|
||||
"extra": {}
|
||||
}
|
||||
{"revision": 0, "last_node_id": 13, "last_link_id": 0, "nodes": [{"id": 13, "type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "pos": [1120, 330], "size": [240, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": null}, {"name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "title": "Video Upscale(GAN x4)", "properties": {"proxyWidgets": [["-1", "model_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 13, "lastLinkId": 19, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Upscale(GAN x4)", "inputNode": {"id": -10, "bounding": [550, 460, 120, 80]}, "outputNode": {"id": -20, "bounding": [1490, 460, 120, 60]}, "inputs": [{"id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6", "name": "video", "type": "VIDEO", "linkIds": [10], "localized_name": "video", "pos": [650, 480]}, {"id": "2e23a087-caa8-4d65-99e6-662761aa905a", "name": "model_name", "type": "COMBO", "linkIds": [19], "pos": [650, 500]}], "outputs": [{"id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70", "name": "VIDEO", "type": "VIDEO", "linkIds": [15], "localized_name": "VIDEO", "pos": [1510, 480]}], "widgets": [], "nodes": [{"id": 2, "type": "ImageUpscaleWithModel", "pos": [1110, 450], "size": [320, 46], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "upscale_model", "name": "upscale_model", "type": "UPSCALE_MODEL", "link": 1}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 14}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "ImageUpscaleWithModel"}}, {"id": 11, "type": "CreateVideo", "pos": [1110, 550], "size": [320, 78], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 13}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 16}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 12}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [15]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [30]}, {"id": 10, "type": "GetVideoComponents", "pos": [1110, 330], "size": [320, 70], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 10}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [14]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": [16]}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": [12]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "GetVideoComponents"}}, {"id": 1, "type": "UpscaleModelLoader", "pos": [750, 450], "size": [280, 60], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 19}], "outputs": [{"localized_name": "UPSCALE_MODEL", "name": "UPSCALE_MODEL", "type": "UPSCALE_MODEL", "links": [1]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "UpscaleModelLoader", "models": [{"name": "RealESRGAN_x4plus.safetensors", "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", "directory": "upscale_models"}]}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "groups": [], "links": [{"id": 1, "origin_id": 1, "origin_slot": 0, "target_id": 2, "target_slot": 0, "type": "UPSCALE_MODEL"}, {"id": 14, "origin_id": 10, "origin_slot": 0, "target_id": 2, "target_slot": 1, "type": "IMAGE"}, {"id": 13, "origin_id": 2, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "IMAGE"}, {"id": 16, "origin_id": 10, "origin_slot": 1, "target_id": 11, "target_slot": 1, "type": "AUDIO"}, {"id": 12, "origin_id": 10, "origin_slot": 2, "target_id": 11, "target_slot": 2, "type": "FLOAT"}, {"id": 10, "origin_id": -10, "origin_slot": 0, "target_id": 10, "target_slot": 0, "type": "VIDEO"}, {"id": 15, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 19, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Enhance video"}]}, "extra": {}}
|
||||
|
||||
@@ -611,7 +611,6 @@ class AceStepDiTModel(nn.Module):
|
||||
intermediate_size,
|
||||
patch_size,
|
||||
audio_acoustic_hidden_dim,
|
||||
condition_dim=None,
|
||||
layer_types=None,
|
||||
sliding_window=128,
|
||||
rms_norm_eps=1e-6,
|
||||
@@ -641,7 +640,7 @@ class AceStepDiTModel(nn.Module):
|
||||
|
||||
self.time_embed = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations)
|
||||
self.time_embed_r = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations)
|
||||
self.condition_embedder = Linear(condition_dim, hidden_size, dtype=dtype, device=device)
|
||||
self.condition_embedder = Linear(hidden_size, hidden_size, dtype=dtype, device=device)
|
||||
|
||||
if layer_types is None:
|
||||
layer_types = ["full_attention"] * num_layers
|
||||
@@ -1036,9 +1035,6 @@ class AceStepConditionGenerationModel(nn.Module):
|
||||
fsq_dim=2048,
|
||||
fsq_levels=[8, 8, 8, 5, 5, 5],
|
||||
fsq_input_num_quantizers=1,
|
||||
encoder_hidden_size=2048,
|
||||
encoder_intermediate_size=6144,
|
||||
encoder_num_heads=16,
|
||||
audio_model=None,
|
||||
dtype=None,
|
||||
device=None,
|
||||
@@ -1058,24 +1054,24 @@ class AceStepConditionGenerationModel(nn.Module):
|
||||
|
||||
self.decoder = AceStepDiTModel(
|
||||
in_channels, hidden_size, num_dit_layers, num_heads, num_kv_heads, head_dim,
|
||||
intermediate_size, patch_size, audio_acoustic_hidden_dim, condition_dim=encoder_hidden_size,
|
||||
intermediate_size, patch_size, audio_acoustic_hidden_dim,
|
||||
layer_types=layer_types, sliding_window=sliding_window, rms_norm_eps=rms_norm_eps,
|
||||
dtype=dtype, device=device, operations=operations
|
||||
)
|
||||
self.encoder = AceStepConditionEncoder(
|
||||
text_hidden_dim, timbre_hidden_dim, encoder_hidden_size, num_lyric_layers, num_timbre_layers,
|
||||
encoder_num_heads, num_kv_heads, head_dim, encoder_intermediate_size, rms_norm_eps,
|
||||
text_hidden_dim, timbre_hidden_dim, hidden_size, num_lyric_layers, num_timbre_layers,
|
||||
num_heads, num_kv_heads, head_dim, intermediate_size, rms_norm_eps,
|
||||
dtype=dtype, device=device, operations=operations
|
||||
)
|
||||
self.tokenizer = AceStepAudioTokenizer(
|
||||
audio_acoustic_hidden_dim, encoder_hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps,
|
||||
audio_acoustic_hidden_dim, hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps,
|
||||
dtype=dtype, device=device, operations=operations
|
||||
)
|
||||
self.detokenizer = AudioTokenDetokenizer(
|
||||
encoder_hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim,
|
||||
hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim,
|
||||
dtype=dtype, device=device, operations=operations
|
||||
)
|
||||
self.null_condition_emb = nn.Parameter(torch.empty(1, 1, encoder_hidden_size, dtype=dtype, device=device))
|
||||
self.null_condition_emb = nn.Parameter(torch.empty(1, 1, hidden_size, dtype=dtype, device=device))
|
||||
|
||||
def prepare_condition(
|
||||
self,
|
||||
|
||||
@@ -155,7 +155,6 @@ class AutoencodingEngineLegacy(AutoencodingEngine):
|
||||
def __init__(self, embed_dim: int, **kwargs):
|
||||
self.max_batch_size = kwargs.pop("max_batch_size", None)
|
||||
ddconfig = kwargs.pop("ddconfig")
|
||||
decoder_ddconfig = kwargs.pop("decoder_ddconfig", ddconfig)
|
||||
super().__init__(
|
||||
encoder_config={
|
||||
"target": "comfy.ldm.modules.diffusionmodules.model.Encoder",
|
||||
@@ -163,7 +162,7 @@ class AutoencodingEngineLegacy(AutoencodingEngine):
|
||||
},
|
||||
decoder_config={
|
||||
"target": "comfy.ldm.modules.diffusionmodules.model.Decoder",
|
||||
"params": decoder_ddconfig,
|
||||
"params": ddconfig,
|
||||
},
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
@@ -3,9 +3,12 @@ from ..diffusionmodules.openaimodel import Timestep
|
||||
import torch
|
||||
|
||||
class CLIPEmbeddingNoiseAugmentation(ImageConcatWithNoiseAugmentation):
|
||||
def __init__(self, *args, timestep_dim=256, **kwargs):
|
||||
def __init__(self, *args, clip_stats_path=None, timestep_dim=256, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
clip_mean, clip_std = torch.zeros(timestep_dim), torch.ones(timestep_dim)
|
||||
if clip_stats_path is None:
|
||||
clip_mean, clip_std = torch.zeros(timestep_dim), torch.ones(timestep_dim)
|
||||
else:
|
||||
clip_mean, clip_std = torch.load(clip_stats_path, map_location="cpu")
|
||||
self.register_buffer("data_mean", clip_mean[None, :], persistent=False)
|
||||
self.register_buffer("data_std", clip_std[None, :], persistent=False)
|
||||
self.time_embed = Timestep(timestep_dim)
|
||||
|
||||
@@ -696,15 +696,6 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
|
||||
if '{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix) in state_dict_keys:
|
||||
dit_config = {}
|
||||
dit_config["audio_model"] = "ace1.5"
|
||||
head_dim = 128
|
||||
dit_config["hidden_size"] = state_dict['{}decoder.layers.0.self_attn_norm.weight'.format(key_prefix)].shape[0]
|
||||
dit_config["intermediate_size"] = state_dict['{}decoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0]
|
||||
dit_config["num_heads"] = state_dict['{}decoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim
|
||||
|
||||
dit_config["encoder_hidden_size"] = state_dict['{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix)].shape[0]
|
||||
dit_config["encoder_num_heads"] = state_dict['{}encoder.lyric_encoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim
|
||||
dit_config["encoder_intermediate_size"] = state_dict['{}encoder.lyric_encoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0]
|
||||
dit_config["num_dit_layers"] = count_blocks(state_dict_keys, '{}decoder.layers.'.format(key_prefix) + '{}.')
|
||||
return dit_config
|
||||
|
||||
if '{}encoder.pan_blocks.1.cv4.conv.weight'.format(key_prefix) in state_dict_keys: # RT-DETR_v4
|
||||
|
||||
13
comfy/sd.py
13
comfy/sd.py
@@ -556,19 +556,12 @@ class VAE:
|
||||
old_memory_used_decode = self.memory_used_decode
|
||||
self.memory_used_decode = lambda shape, dtype: old_memory_used_decode(shape, dtype) * 4.0
|
||||
|
||||
decoder_ch = sd['decoder.conv_in.weight'].shape[0] // ddconfig['ch_mult'][-1]
|
||||
if decoder_ch != ddconfig['ch']:
|
||||
decoder_ddconfig = ddconfig.copy()
|
||||
decoder_ddconfig['ch'] = decoder_ch
|
||||
else:
|
||||
decoder_ddconfig = None
|
||||
|
||||
if 'post_quant_conv.weight' in sd:
|
||||
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1], **({"decoder_ddconfig": decoder_ddconfig} if decoder_ddconfig is not None else {}))
|
||||
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': decoder_ddconfig if decoder_ddconfig is not None else ddconfig})
|
||||
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
|
||||
elif "decoder.layers.1.layers.0.beta" in sd:
|
||||
config = {}
|
||||
param_key = None
|
||||
@@ -1752,8 +1745,6 @@ def load_diffusion_model_state_dict(sd, model_options={}, metadata=None, disable
|
||||
temp_sd = comfy.utils.state_dict_prefix_replace(sd, {diffusion_model_prefix: ""}, filter_keys=True)
|
||||
if len(temp_sd) > 0:
|
||||
sd = temp_sd
|
||||
if custom_operations is None:
|
||||
sd, metadata = comfy.utils.convert_old_quants(sd, "", metadata=metadata)
|
||||
|
||||
parameters = comfy.utils.calculate_parameters(sd)
|
||||
weight_dtype = comfy.utils.weight_dtype(sd)
|
||||
|
||||
@@ -43,9 +43,55 @@ class UploadType(str, Enum):
|
||||
model = "file_upload"
|
||||
|
||||
|
||||
class RemoteItemSchema:
|
||||
"""Describes how to map API response objects to rich dropdown items.
|
||||
|
||||
All *_field parameters use dot-path notation (e.g. ``"labels.gender"``).
|
||||
``label_field`` additionally supports template strings with ``{field}``
|
||||
placeholders (e.g. ``"{name} ({labels.accent})"``).
|
||||
"""
|
||||
def __init__(
|
||||
self,
|
||||
value_field: str,
|
||||
label_field: str,
|
||||
preview_url_field: str | None = None,
|
||||
preview_type: Literal["image", "video", "audio"] = "image",
|
||||
description_field: str | None = None,
|
||||
search_fields: list[str] | None = None,
|
||||
filter_field: str | None = None,
|
||||
):
|
||||
self.value_field = value_field
|
||||
"""Dot-path to the unique identifier within each item. This value is stored in the widget and passed to execute()."""
|
||||
self.label_field = label_field
|
||||
"""Dot-path to the display name, or a template string with {field} placeholders."""
|
||||
self.preview_url_field = preview_url_field
|
||||
"""Dot-path to a preview media URL. If None, no preview is shown."""
|
||||
self.preview_type = preview_type
|
||||
"""How to render the preview: "image", "video", or "audio"."""
|
||||
self.description_field = description_field
|
||||
"""Optional dot-path or template for a subtitle line shown below the label."""
|
||||
self.search_fields = search_fields
|
||||
"""Dot-paths to fields included in the search index. Defaults to [label_field]."""
|
||||
self.filter_field = filter_field
|
||||
"""Optional dot-path to a categorical field for filter tabs."""
|
||||
|
||||
def as_dict(self):
|
||||
return prune_dict({
|
||||
"value_field": self.value_field,
|
||||
"label_field": self.label_field,
|
||||
"preview_url_field": self.preview_url_field,
|
||||
"preview_type": self.preview_type,
|
||||
"description_field": self.description_field,
|
||||
"search_fields": self.search_fields,
|
||||
"filter_field": self.filter_field,
|
||||
})
|
||||
|
||||
|
||||
class RemoteOptions:
|
||||
def __init__(self, route: str, refresh_button: bool, control_after_refresh: Literal["first", "last"]="first",
|
||||
timeout: int=None, max_retries: int=None, refresh: int=None):
|
||||
timeout: int=None, max_retries: int=None, refresh: int=None,
|
||||
response_key: str=None, query_params: dict[str, str]=None,
|
||||
item_schema: RemoteItemSchema=None):
|
||||
self.route = route
|
||||
"""The route to the remote source."""
|
||||
self.refresh_button = refresh_button
|
||||
@@ -58,6 +104,12 @@ class RemoteOptions:
|
||||
"""The maximum number of retries before aborting the request."""
|
||||
self.refresh = refresh
|
||||
"""The TTL of the remote input's value in milliseconds. Specifies the interval at which the remote input's value is refreshed."""
|
||||
self.response_key = response_key
|
||||
"""Dot-path to the items array in the response. If None, the entire response is used."""
|
||||
self.query_params = query_params
|
||||
"""Static query parameters appended to the request URL."""
|
||||
self.item_schema = item_schema
|
||||
"""When present, the frontend renders a rich dropdown with previews instead of a plain combo widget."""
|
||||
|
||||
def as_dict(self):
|
||||
return prune_dict({
|
||||
@@ -67,6 +119,9 @@ class RemoteOptions:
|
||||
"timeout": self.timeout,
|
||||
"max_retries": self.max_retries,
|
||||
"refresh": self.refresh,
|
||||
"response_key": self.response_key,
|
||||
"query_params": self.query_params,
|
||||
"item_schema": self.item_schema.as_dict() if self.item_schema else None,
|
||||
})
|
||||
|
||||
|
||||
@@ -2184,6 +2239,7 @@ class NodeReplace:
|
||||
__all__ = [
|
||||
"FolderType",
|
||||
"UploadType",
|
||||
"RemoteItemSchema",
|
||||
"RemoteOptions",
|
||||
"NumberDisplay",
|
||||
"ControlAfterGenerate",
|
||||
|
||||
49
comfy_api_nodes/apis/phota_labs.py
Normal file
49
comfy_api_nodes/apis/phota_labs.py
Normal file
@@ -0,0 +1,49 @@
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class PhotaGenerateRequest(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
num_output_images: int = Field(1)
|
||||
aspect_ratio: str = Field(...)
|
||||
resolution: str = Field(...)
|
||||
profile_ids: list[str] | None = Field(None)
|
||||
|
||||
|
||||
class PhotaEditRequest(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
images: list[str] = Field(...)
|
||||
num_output_images: int = Field(1)
|
||||
aspect_ratio: str = Field(...)
|
||||
resolution: str = Field(...)
|
||||
profile_ids: list[str] | None = Field(None)
|
||||
|
||||
|
||||
class PhotaEnhanceRequest(BaseModel):
|
||||
image: str = Field(...)
|
||||
num_output_images: int = Field(1)
|
||||
|
||||
|
||||
class PhotaKnownGeneratedSubjectCounts(BaseModel):
|
||||
counts: dict[str, int] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class PhotoStudioResponse(BaseModel):
|
||||
images: list[str] = Field(..., description="Base64-encoded PNG output images.")
|
||||
known_subjects: PhotaKnownGeneratedSubjectCounts = Field(default_factory=PhotaKnownGeneratedSubjectCounts)
|
||||
|
||||
|
||||
class PhotaAddProfileRequest(BaseModel):
|
||||
image_urls: list[str] = Field(...)
|
||||
|
||||
|
||||
class PhotaAddProfileResponse(BaseModel):
|
||||
profile_id: str = Field(...)
|
||||
|
||||
|
||||
class PhotaProfileStatusResponse(BaseModel):
|
||||
profile_id: str = Field(...)
|
||||
status: str = Field(
|
||||
...,
|
||||
description="Current profile status: VALIDATING, QUEUING, IN_PROGRESS, READY, ERROR, or INACTIVE.",
|
||||
)
|
||||
message: str | None = Field(default=None, description="Optional error or status message.")
|
||||
@@ -1,226 +0,0 @@
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class Text2ImageInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
|
||||
|
||||
class Image2ImageInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
images: list[str] = Field(..., min_length=1, max_length=2)
|
||||
|
||||
|
||||
class Text2VideoInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
audio_url: str | None = Field(None)
|
||||
|
||||
|
||||
class Image2VideoInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
img_url: str = Field(...)
|
||||
audio_url: str | None = Field(None)
|
||||
|
||||
|
||||
class Reference2VideoInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
reference_video_urls: list[str] = Field(...)
|
||||
|
||||
|
||||
class Txt2ImageParametersField(BaseModel):
|
||||
size: str = Field(...)
|
||||
n: int = Field(1, description="Number of images to generate.") # we support only value=1
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
prompt_extend: bool = Field(True)
|
||||
watermark: bool = Field(False)
|
||||
|
||||
|
||||
class Image2ImageParametersField(BaseModel):
|
||||
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(False)
|
||||
|
||||
|
||||
class Text2VideoParametersField(BaseModel):
|
||||
size: str = Field(...)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
duration: int = Field(5, ge=5, le=15)
|
||||
prompt_extend: bool = Field(True)
|
||||
watermark: bool = Field(False)
|
||||
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=15)
|
||||
prompt_extend: bool = Field(True)
|
||||
watermark: bool = Field(False)
|
||||
audio: bool = Field(False, description="Whether to generate audio automatically.")
|
||||
shot_type: str = Field("single")
|
||||
|
||||
|
||||
class Reference2VideoParametersField(BaseModel):
|
||||
size: str = Field(...)
|
||||
duration: int = Field(5, ge=5, le=15)
|
||||
shot_type: str = Field("single")
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
watermark: bool = Field(False)
|
||||
|
||||
|
||||
class Text2ImageTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Text2ImageInputField = Field(...)
|
||||
parameters: Txt2ImageParametersField = Field(...)
|
||||
|
||||
|
||||
class Image2ImageTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Image2ImageInputField = Field(...)
|
||||
parameters: Image2ImageParametersField = Field(...)
|
||||
|
||||
|
||||
class Text2VideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Text2VideoInputField = Field(...)
|
||||
parameters: Text2VideoParametersField = Field(...)
|
||||
|
||||
|
||||
class Image2VideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Image2VideoInputField = Field(...)
|
||||
parameters: Image2VideoParametersField = Field(...)
|
||||
|
||||
|
||||
class Reference2VideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Reference2VideoInputField = Field(...)
|
||||
parameters: Reference2VideoParametersField = Field(...)
|
||||
|
||||
|
||||
class Wan27MediaItem(BaseModel):
|
||||
type: str = Field(...)
|
||||
url: str = Field(...)
|
||||
|
||||
|
||||
class Wan27ReferenceVideoInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
negative_prompt: str | None = Field(None)
|
||||
media: list[Wan27MediaItem] = Field(...)
|
||||
|
||||
|
||||
class Wan27ReferenceVideoParametersField(BaseModel):
|
||||
resolution: str = Field(...)
|
||||
ratio: str | None = Field(None)
|
||||
duration: int = Field(5, ge=2, le=10)
|
||||
watermark: bool = Field(False)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
|
||||
|
||||
class Wan27ReferenceVideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Wan27ReferenceVideoInputField = Field(...)
|
||||
parameters: Wan27ReferenceVideoParametersField = Field(...)
|
||||
|
||||
|
||||
class Wan27ImageToVideoInputField(BaseModel):
|
||||
prompt: str | None = Field(None)
|
||||
negative_prompt: str | None = Field(None)
|
||||
media: list[Wan27MediaItem] = Field(...)
|
||||
|
||||
|
||||
class Wan27ImageToVideoParametersField(BaseModel):
|
||||
resolution: str = Field(...)
|
||||
duration: int = Field(5, ge=2, le=15)
|
||||
prompt_extend: bool = Field(True)
|
||||
watermark: bool = Field(False)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
|
||||
|
||||
class Wan27ImageToVideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Wan27ImageToVideoInputField = Field(...)
|
||||
parameters: Wan27ImageToVideoParametersField = Field(...)
|
||||
|
||||
|
||||
class Wan27VideoEditInputField(BaseModel):
|
||||
prompt: str = Field(...)
|
||||
media: list[Wan27MediaItem] = Field(...)
|
||||
|
||||
|
||||
class Wan27VideoEditParametersField(BaseModel):
|
||||
resolution: str = Field(...)
|
||||
ratio: str | None = Field(None)
|
||||
duration: int = Field(0)
|
||||
audio_setting: str = Field("auto")
|
||||
watermark: bool = Field(False)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
|
||||
|
||||
class Wan27VideoEditTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Wan27VideoEditInputField = Field(...)
|
||||
parameters: Wan27VideoEditParametersField = Field(...)
|
||||
|
||||
|
||||
class Wan27Text2VideoParametersField(BaseModel):
|
||||
resolution: str = Field(...)
|
||||
ratio: str | None = Field(None)
|
||||
duration: int = Field(5, ge=2, le=15)
|
||||
prompt_extend: bool = Field(True)
|
||||
watermark: bool = Field(False)
|
||||
seed: int = Field(..., ge=0, le=2147483647)
|
||||
|
||||
|
||||
class Wan27Text2VideoTaskCreationRequest(BaseModel):
|
||||
model: str = Field(...)
|
||||
input: Text2VideoInputField = Field(...)
|
||||
parameters: Wan27Text2VideoParametersField = Field(...)
|
||||
|
||||
|
||||
class TaskCreationOutputField(BaseModel):
|
||||
task_id: str = Field(...)
|
||||
task_status: str = Field(...)
|
||||
|
||||
|
||||
class TaskCreationResponse(BaseModel):
|
||||
output: TaskCreationOutputField | None = Field(None)
|
||||
request_id: str = Field(...)
|
||||
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: 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: list[TaskResult] | None = Field(None)
|
||||
|
||||
|
||||
class VideoTaskStatusOutputField(TaskCreationOutputField):
|
||||
task_id: str = Field(...)
|
||||
task_status: str = Field(...)
|
||||
video_url: str | None = Field(None)
|
||||
code: str | None = Field(None)
|
||||
message: str | None = Field(None)
|
||||
|
||||
|
||||
class ImageTaskStatusResponse(BaseModel):
|
||||
output: ImageTaskStatusOutputField | None = Field(None)
|
||||
request_id: str = Field(...)
|
||||
|
||||
|
||||
class VideoTaskStatusResponse(BaseModel):
|
||||
output: VideoTaskStatusOutputField | None = Field(None)
|
||||
request_id: str = Field(...)
|
||||
@@ -233,6 +233,45 @@ class ElevenLabsVoiceSelector(IO.ComfyNode):
|
||||
return IO.NodeOutput(voice_id)
|
||||
|
||||
|
||||
class ElevenLabsRichVoiceSelector(IO.ComfyNode):
|
||||
@classmethod
|
||||
def define_schema(cls) -> IO.Schema:
|
||||
return IO.Schema(
|
||||
node_id="ElevenLabsRichVoiceSelector",
|
||||
display_name="ElevenLabs Voice Selector (Rich)",
|
||||
category="api node/audio/ElevenLabs",
|
||||
description="Select an ElevenLabs voice with audio preview and rich metadata.",
|
||||
inputs=[
|
||||
IO.Combo.Input(
|
||||
"voice",
|
||||
options=ELEVENLABS_VOICE_OPTIONS,
|
||||
remote=IO.RemoteOptions(
|
||||
route="http://localhost:9000/elevenlabs/voices",
|
||||
refresh_button=True,
|
||||
item_schema=IO.RemoteItemSchema(
|
||||
value_field="voice_id",
|
||||
label_field="name",
|
||||
preview_url_field="preview_url",
|
||||
preview_type="audio",
|
||||
search_fields=["name", "labels.gender", "labels.accent"],
|
||||
filter_field="labels.use_case",
|
||||
),
|
||||
),
|
||||
tooltip="Choose a voice with audio preview.",
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Custom(ELEVENLABS_VOICE).Output(display_name="voice"),
|
||||
],
|
||||
is_api_node=False,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def execute(cls, voice: str) -> IO.NodeOutput:
|
||||
# voice is already the voice_id from item_schema.value_field
|
||||
return IO.NodeOutput(voice)
|
||||
|
||||
|
||||
class ElevenLabsTextToSpeech(IO.ComfyNode):
|
||||
@classmethod
|
||||
def define_schema(cls) -> IO.Schema:
|
||||
@@ -911,6 +950,7 @@ class ElevenLabsExtension(ComfyExtension):
|
||||
return [
|
||||
ElevenLabsSpeechToText,
|
||||
ElevenLabsVoiceSelector,
|
||||
ElevenLabsRichVoiceSelector,
|
||||
ElevenLabsTextToSpeech,
|
||||
ElevenLabsAudioIsolation,
|
||||
ElevenLabsTextToSoundEffects,
|
||||
|
||||
350
comfy_api_nodes/nodes_phota_labs.py
Normal file
350
comfy_api_nodes/nodes_phota_labs.py
Normal file
@@ -0,0 +1,350 @@
|
||||
import base64
|
||||
from io import BytesIO
|
||||
|
||||
from typing_extensions import override
|
||||
|
||||
from comfy_api.latest import IO, ComfyExtension, Input
|
||||
from comfy_api_nodes.apis.phota_labs import (
|
||||
PhotaAddProfileRequest,
|
||||
PhotaAddProfileResponse,
|
||||
PhotaEditRequest,
|
||||
PhotaEnhanceRequest,
|
||||
PhotaGenerateRequest,
|
||||
PhotaProfileStatusResponse,
|
||||
PhotoStudioResponse,
|
||||
)
|
||||
from comfy_api_nodes.util import (
|
||||
ApiEndpoint,
|
||||
bytesio_to_image_tensor,
|
||||
poll_op,
|
||||
sync_op,
|
||||
upload_images_to_comfyapi,
|
||||
upload_image_to_comfyapi,
|
||||
validate_string,
|
||||
)
|
||||
|
||||
# Direct API endpoint (comment out this class to use proxy)
|
||||
class ApiEndpoint(ApiEndpoint):
|
||||
"""Temporary override to use direct API instead of proxy."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
path: str,
|
||||
method: str = "GET",
|
||||
*,
|
||||
query_params: dict | None = None,
|
||||
headers: dict | None = None,
|
||||
):
|
||||
self.path = path.replace("/proxy/phota/", "https://api.photalabs.com/")
|
||||
self.method = method
|
||||
self.query_params = query_params or {}
|
||||
self.headers = headers or {}
|
||||
if "api.photalabs.com" in self.path:
|
||||
self.headers["X-API-Key"] = "YOUR_PHOTA_API_KEY"
|
||||
|
||||
|
||||
PHOTA_LABS_PROFILE_ID = "PHOTA_LABS_PROFILE_ID"
|
||||
|
||||
|
||||
class PhotaLabsGenerate(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="PhotaLabsGenerate",
|
||||
display_name="Phota Labs Generate",
|
||||
category="api node/image/Phota Labs",
|
||||
description="Generate images from a text prompt using Phota Labs.",
|
||||
inputs=[
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
tooltip="Text prompt describing the desired image.",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=["auto", "1:1", "3:4", "4:3", "9:16", "16:9"],
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"resolution",
|
||||
options=["1K", "4K"],
|
||||
),
|
||||
],
|
||||
outputs=[IO.Image.Output()],
|
||||
hidden=[
|
||||
IO.Hidden.auth_token_comfy_org,
|
||||
IO.Hidden.api_key_comfy_org,
|
||||
IO.Hidden.unique_id,
|
||||
],
|
||||
is_api_node=True,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
prompt: str,
|
||||
aspect_ratio: str,
|
||||
resolution: str,
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False, min_length=1)
|
||||
pid_list = None # list(profile_ids.values()) if profile_ids else None
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/phota/v1/phota/generate", method="POST"),
|
||||
response_model=PhotoStudioResponse,
|
||||
data=PhotaGenerateRequest(
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect_ratio,
|
||||
resolution=resolution,
|
||||
profile_ids=pid_list or None,
|
||||
),
|
||||
)
|
||||
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(base64.b64decode(response.images[0]))))
|
||||
|
||||
|
||||
class PhotaLabsEdit(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="PhotaLabsEdit",
|
||||
display_name="Phota Labs Edit",
|
||||
category="api node/image/Phota Labs",
|
||||
description="Edit images based on a text prompt using Phota Labs. "
|
||||
"Provide input images and a prompt describing the desired edit.",
|
||||
inputs=[
|
||||
IO.Autogrow.Input(
|
||||
"images",
|
||||
template=IO.Autogrow.TemplatePrefix(
|
||||
IO.Image.Input("image"),
|
||||
prefix="image",
|
||||
min=1,
|
||||
max=10,
|
||||
),
|
||||
),
|
||||
IO.String.Input(
|
||||
"prompt",
|
||||
multiline=True,
|
||||
default="",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=["auto", "1:1", "3:4", "4:3", "9:16", "16:9"],
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"resolution",
|
||||
options=["1K", "4K"],
|
||||
),
|
||||
IO.Autogrow.Input(
|
||||
"profile_ids",
|
||||
template=IO.Autogrow.TemplatePrefix(
|
||||
IO.Custom(PHOTA_LABS_PROFILE_ID).Input("profile_id"),
|
||||
prefix="profile_id",
|
||||
min=0,
|
||||
max=5,
|
||||
),
|
||||
),
|
||||
],
|
||||
outputs=[IO.Image.Output()],
|
||||
hidden=[
|
||||
IO.Hidden.auth_token_comfy_org,
|
||||
IO.Hidden.api_key_comfy_org,
|
||||
IO.Hidden.unique_id,
|
||||
],
|
||||
is_api_node=True,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
images: IO.Autogrow.Type,
|
||||
prompt: str,
|
||||
aspect_ratio: str,
|
||||
resolution: str,
|
||||
profile_ids: IO.Autogrow.Type = None,
|
||||
) -> IO.NodeOutput:
|
||||
validate_string(prompt, strip_whitespace=False, min_length=1)
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/phota/v1/phota/edit", method="POST"),
|
||||
response_model=PhotoStudioResponse,
|
||||
data=PhotaEditRequest(
|
||||
prompt=prompt,
|
||||
images=await upload_images_to_comfyapi(cls, list(images.values()), max_images=10),
|
||||
aspect_ratio=aspect_ratio,
|
||||
resolution=resolution,
|
||||
profile_ids=list(profile_ids.values()) if profile_ids else None,
|
||||
),
|
||||
)
|
||||
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(base64.b64decode(response.images[0]))))
|
||||
|
||||
|
||||
class PhotaLabsEnhance(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="PhotaLabsEnhance",
|
||||
display_name="Phota Labs Enhance",
|
||||
category="api node/image/Phota Labs",
|
||||
description="Automatically enhance a photo using Phota Labs. "
|
||||
"No text prompt is required — enhancement parameters are inferred automatically.",
|
||||
inputs=[
|
||||
IO.Image.Input(
|
||||
"image",
|
||||
tooltip="Input image to enhance.",
|
||||
),
|
||||
IO.Autogrow.Input(
|
||||
"profile_ids",
|
||||
template=IO.Autogrow.TemplatePrefix(
|
||||
IO.Custom(PHOTA_LABS_PROFILE_ID).Input("profile_id"),
|
||||
prefix="profile_id",
|
||||
min=0,
|
||||
max=5,
|
||||
),
|
||||
),
|
||||
],
|
||||
outputs=[IO.Image.Output()],
|
||||
hidden=[
|
||||
IO.Hidden.auth_token_comfy_org,
|
||||
IO.Hidden.api_key_comfy_org,
|
||||
IO.Hidden.unique_id,
|
||||
],
|
||||
is_api_node=True,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
image: Input.Image,
|
||||
profile_ids: IO.Autogrow.Type = None,
|
||||
) -> IO.NodeOutput:
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/phota/v1/phota/enhance", method="POST"),
|
||||
response_model=PhotoStudioResponse,
|
||||
data=PhotaEnhanceRequest(
|
||||
image=await upload_image_to_comfyapi(cls, image),
|
||||
),
|
||||
)
|
||||
return IO.NodeOutput(bytesio_to_image_tensor(BytesIO(base64.b64decode(response.images[0]))))
|
||||
|
||||
|
||||
class PhotaLabsSelectProfile(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="PhotaLabsSelectProfile",
|
||||
display_name="Phota Labs Select Profile",
|
||||
category="api node/image/Phota Labs",
|
||||
description="Select a trained Phota Labs profile for use in generation.",
|
||||
inputs=[
|
||||
IO.Combo.Input(
|
||||
"profile_id",
|
||||
options=[],
|
||||
remote=IO.RemoteOptions(
|
||||
route="http://localhost:9000/phota/profiles",
|
||||
refresh_button=True,
|
||||
item_schema=IO.RemoteItemSchema(
|
||||
value_field="profile_id",
|
||||
label_field="profile_id",
|
||||
preview_url_field="preview_url",
|
||||
preview_type="image",
|
||||
),
|
||||
),
|
||||
),
|
||||
],
|
||||
outputs=[IO.Custom(PHOTA_LABS_PROFILE_ID).Output(display_name="profile_id")],
|
||||
hidden=[
|
||||
IO.Hidden.auth_token_comfy_org,
|
||||
IO.Hidden.api_key_comfy_org,
|
||||
IO.Hidden.unique_id,
|
||||
],
|
||||
is_api_node=True,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(cls, profile_id: str) -> IO.NodeOutput:
|
||||
return IO.NodeOutput(profile_id)
|
||||
|
||||
|
||||
class PhotaLabsAddProfile(IO.ComfyNode):
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="PhotaLabsAddProfile",
|
||||
display_name="Phota Labs Add Profile",
|
||||
category="api node/image/Phota Labs",
|
||||
description="Create a training profile from 30-50 reference images using Phota Labs. "
|
||||
"Uploads images and starts asynchronous training, returning the profile ID once training is queued.",
|
||||
inputs=[
|
||||
IO.Autogrow.Input(
|
||||
"images",
|
||||
template=IO.Autogrow.TemplatePrefix(
|
||||
IO.Image.Input("image"),
|
||||
prefix="image",
|
||||
min=30,
|
||||
max=50,
|
||||
),
|
||||
),
|
||||
],
|
||||
outputs=[
|
||||
IO.Custom(PHOTA_LABS_PROFILE_ID).Output(display_name="profile_id"),
|
||||
IO.String.Output(display_name="status"),
|
||||
],
|
||||
hidden=[
|
||||
IO.Hidden.auth_token_comfy_org,
|
||||
IO.Hidden.api_key_comfy_org,
|
||||
IO.Hidden.unique_id,
|
||||
],
|
||||
is_api_node=True,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
images: IO.Autogrow.Type,
|
||||
) -> IO.NodeOutput:
|
||||
image_urls = await upload_images_to_comfyapi(
|
||||
cls,
|
||||
list(images.values()),
|
||||
max_images=50,
|
||||
wait_label="Uploading training images",
|
||||
)
|
||||
response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path="/proxy/phota/v1/phota/profiles/add", method="POST"),
|
||||
response_model=PhotaAddProfileResponse,
|
||||
data=PhotaAddProfileRequest(image_urls=image_urls),
|
||||
)
|
||||
# Poll until validation passes and training is queued/in-progress/ready
|
||||
status_response = await poll_op(
|
||||
cls,
|
||||
ApiEndpoint(
|
||||
path=f"/proxy/phota/v1/phota/profiles/{response.profile_id}/status"
|
||||
),
|
||||
response_model=PhotaProfileStatusResponse,
|
||||
status_extractor=lambda r: r.status,
|
||||
completed_statuses=["QUEUING", "IN_PROGRESS", "READY"],
|
||||
failed_statuses=["ERROR", "INACTIVE"],
|
||||
)
|
||||
return IO.NodeOutput(response.profile_id, status_response.status)
|
||||
|
||||
|
||||
class PhotaLabsExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
|
||||
return [
|
||||
PhotaLabsGenerate,
|
||||
PhotaLabsEdit,
|
||||
PhotaLabsEnhance,
|
||||
PhotaLabsSelectProfile,
|
||||
PhotaLabsAddProfile,
|
||||
]
|
||||
|
||||
|
||||
async def comfy_entrypoint() -> PhotaLabsExtension:
|
||||
return PhotaLabsExtension()
|
||||
@@ -24,9 +24,8 @@ from comfy_api_nodes.util import (
|
||||
AVERAGE_DURATION_VIDEO_GEN = 32
|
||||
MODELS_MAP = {
|
||||
"veo-2.0-generate-001": "veo-2.0-generate-001",
|
||||
"veo-3.1-generate": "veo-3.1-generate-001",
|
||||
"veo-3.1-fast-generate": "veo-3.1-fast-generate-001",
|
||||
"veo-3.1-lite": "veo-3.1-lite-generate-001",
|
||||
"veo-3.1-generate": "veo-3.1-generate-preview",
|
||||
"veo-3.1-fast-generate": "veo-3.1-fast-generate-preview",
|
||||
"veo-3.0-generate-001": "veo-3.0-generate-001",
|
||||
"veo-3.0-fast-generate-001": "veo-3.0-fast-generate-001",
|
||||
}
|
||||
@@ -248,8 +247,17 @@ class VeoVideoGenerationNode(IO.ComfyNode):
|
||||
raise Exception("Video generation completed but no video was returned")
|
||||
|
||||
|
||||
class Veo3VideoGenerationNode(IO.ComfyNode):
|
||||
"""Generates videos from text prompts using Google's Veo 3 API."""
|
||||
class Veo3VideoGenerationNode(VeoVideoGenerationNode):
|
||||
"""
|
||||
Generates videos from text prompts using Google's Veo 3 API.
|
||||
|
||||
Supported models:
|
||||
- veo-3.0-generate-001
|
||||
- veo-3.0-fast-generate-001
|
||||
|
||||
This node extends the base Veo node with Veo 3 specific features including
|
||||
audio generation and fixed 8-second duration.
|
||||
"""
|
||||
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
@@ -271,12 +279,6 @@ class Veo3VideoGenerationNode(IO.ComfyNode):
|
||||
default="16:9",
|
||||
tooltip="Aspect ratio of the output video",
|
||||
),
|
||||
IO.Combo.Input(
|
||||
"resolution",
|
||||
options=["720p", "1080p", "4k"],
|
||||
default="720p",
|
||||
tooltip="Output video resolution. 4K is not available for veo-3.1-lite and veo-3.0 models.",
|
||||
),
|
||||
IO.String.Input(
|
||||
"negative_prompt",
|
||||
multiline=True,
|
||||
@@ -287,11 +289,11 @@ class Veo3VideoGenerationNode(IO.ComfyNode):
|
||||
IO.Int.Input(
|
||||
"duration_seconds",
|
||||
default=8,
|
||||
min=4,
|
||||
min=8,
|
||||
max=8,
|
||||
step=2,
|
||||
step=1,
|
||||
display_mode=IO.NumberDisplay.number,
|
||||
tooltip="Duration of the output video in seconds",
|
||||
tooltip="Duration of the output video in seconds (Veo 3 only supports 8 seconds)",
|
||||
optional=True,
|
||||
),
|
||||
IO.Boolean.Input(
|
||||
@@ -330,10 +332,10 @@ class Veo3VideoGenerationNode(IO.ComfyNode):
|
||||
options=[
|
||||
"veo-3.1-generate",
|
||||
"veo-3.1-fast-generate",
|
||||
"veo-3.1-lite",
|
||||
"veo-3.0-generate-001",
|
||||
"veo-3.0-fast-generate-001",
|
||||
],
|
||||
default="veo-3.0-generate-001",
|
||||
tooltip="Veo 3 model to use for video generation",
|
||||
optional=True,
|
||||
),
|
||||
@@ -354,111 +356,21 @@ class Veo3VideoGenerationNode(IO.ComfyNode):
|
||||
],
|
||||
is_api_node=True,
|
||||
price_badge=IO.PriceBadge(
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "resolution", "duration_seconds"]),
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio"]),
|
||||
expr="""
|
||||
(
|
||||
$m := widgets.model;
|
||||
$r := widgets.resolution;
|
||||
$a := widgets.generate_audio;
|
||||
$seconds := widgets.duration_seconds;
|
||||
$pps :=
|
||||
$contains($m, "lite")
|
||||
? ($r = "1080p" ? ($a ? 0.08 : 0.05) : ($a ? 0.05 : 0.03))
|
||||
: $contains($m, "3.1-fast")
|
||||
? ($r = "4k" ? ($a ? 0.30 : 0.25) : $r = "1080p" ? ($a ? 0.12 : 0.10) : ($a ? 0.10 : 0.08))
|
||||
: $contains($m, "3.1-generate")
|
||||
? ($r = "4k" ? ($a ? 0.60 : 0.40) : ($a ? 0.40 : 0.20))
|
||||
: $contains($m, "3.0-fast")
|
||||
? ($a ? 0.15 : 0.10)
|
||||
: ($a ? 0.40 : 0.20);
|
||||
{"type":"usd","usd": $pps * $seconds}
|
||||
($contains($m,"veo-3.0-fast-generate-001") or $contains($m,"veo-3.1-fast-generate"))
|
||||
? {"type":"usd","usd": ($a ? 1.2 : 0.8)}
|
||||
: ($contains($m,"veo-3.0-generate-001") or $contains($m,"veo-3.1-generate"))
|
||||
? {"type":"usd","usd": ($a ? 3.2 : 1.6)}
|
||||
: {"type":"range_usd","min_usd":0.8,"max_usd":3.2}
|
||||
)
|
||||
""",
|
||||
),
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def execute(
|
||||
cls,
|
||||
prompt,
|
||||
aspect_ratio="16:9",
|
||||
resolution="720p",
|
||||
negative_prompt="",
|
||||
duration_seconds=8,
|
||||
enhance_prompt=True,
|
||||
person_generation="ALLOW",
|
||||
seed=0,
|
||||
image=None,
|
||||
model="veo-3.0-generate-001",
|
||||
generate_audio=False,
|
||||
):
|
||||
if "lite" in model and resolution == "4k":
|
||||
raise Exception("4K resolution is not supported by the veo-3.1-lite model.")
|
||||
|
||||
model = MODELS_MAP[model]
|
||||
|
||||
instances = [{"prompt": prompt}]
|
||||
if image is not None:
|
||||
image_base64 = tensor_to_base64_string(image)
|
||||
if image_base64:
|
||||
instances[0]["image"] = {"bytesBase64Encoded": image_base64, "mimeType": "image/png"}
|
||||
|
||||
parameters = {
|
||||
"aspectRatio": aspect_ratio,
|
||||
"personGeneration": person_generation,
|
||||
"durationSeconds": duration_seconds,
|
||||
"enhancePrompt": True,
|
||||
"generateAudio": generate_audio,
|
||||
}
|
||||
if negative_prompt:
|
||||
parameters["negativePrompt"] = negative_prompt
|
||||
if seed > 0:
|
||||
parameters["seed"] = seed
|
||||
if "veo-3.1" in model:
|
||||
parameters["resolution"] = resolution
|
||||
|
||||
initial_response = await sync_op(
|
||||
cls,
|
||||
ApiEndpoint(path=f"/proxy/veo/{model}/generate", method="POST"),
|
||||
response_model=VeoGenVidResponse,
|
||||
data=VeoGenVidRequest(
|
||||
instances=instances,
|
||||
parameters=parameters,
|
||||
),
|
||||
)
|
||||
|
||||
poll_response = await poll_op(
|
||||
cls,
|
||||
ApiEndpoint(path=f"/proxy/veo/{model}/poll", method="POST"),
|
||||
response_model=VeoGenVidPollResponse,
|
||||
status_extractor=lambda r: "completed" if r.done else "pending",
|
||||
data=VeoGenVidPollRequest(operationName=initial_response.name),
|
||||
poll_interval=5.0,
|
||||
estimated_duration=AVERAGE_DURATION_VIDEO_GEN,
|
||||
)
|
||||
|
||||
if poll_response.error:
|
||||
raise Exception(f"Veo API error: {poll_response.error.message} (code: {poll_response.error.code})")
|
||||
|
||||
response = poll_response.response
|
||||
filtered_count = response.raiMediaFilteredCount
|
||||
if filtered_count:
|
||||
reasons = response.raiMediaFilteredReasons or []
|
||||
reason_part = f": {reasons[0]}" if reasons else ""
|
||||
raise Exception(
|
||||
f"Content blocked by Google's Responsible AI filters{reason_part} "
|
||||
f"({filtered_count} video{'s' if filtered_count != 1 else ''} filtered)."
|
||||
)
|
||||
|
||||
if response.videos:
|
||||
video = response.videos[0]
|
||||
if video.bytesBase64Encoded:
|
||||
return IO.NodeOutput(InputImpl.VideoFromFile(BytesIO(base64.b64decode(video.bytesBase64Encoded))))
|
||||
if video.gcsUri:
|
||||
return IO.NodeOutput(await download_url_to_video_output(video.gcsUri))
|
||||
raise Exception("Video returned but no data or URL was provided")
|
||||
raise Exception("Video generation completed but no video was returned")
|
||||
|
||||
|
||||
class Veo3FirstLastFrameNode(IO.ComfyNode):
|
||||
|
||||
@@ -482,7 +394,7 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
|
||||
default="",
|
||||
tooltip="Negative text prompt to guide what to avoid in the video",
|
||||
),
|
||||
IO.Combo.Input("resolution", options=["720p", "1080p", "4k"]),
|
||||
IO.Combo.Input("resolution", options=["720p", "1080p"]),
|
||||
IO.Combo.Input(
|
||||
"aspect_ratio",
|
||||
options=["16:9", "9:16"],
|
||||
@@ -512,7 +424,8 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
|
||||
IO.Image.Input("last_frame", tooltip="End frame"),
|
||||
IO.Combo.Input(
|
||||
"model",
|
||||
options=["veo-3.1-generate", "veo-3.1-fast-generate", "veo-3.1-lite"],
|
||||
options=["veo-3.1-generate", "veo-3.1-fast-generate"],
|
||||
default="veo-3.1-fast-generate",
|
||||
),
|
||||
IO.Boolean.Input(
|
||||
"generate_audio",
|
||||
@@ -530,20 +443,26 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
|
||||
],
|
||||
is_api_node=True,
|
||||
price_badge=IO.PriceBadge(
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "duration", "resolution"]),
|
||||
depends_on=IO.PriceBadgeDepends(widgets=["model", "generate_audio", "duration"]),
|
||||
expr="""
|
||||
(
|
||||
$prices := {
|
||||
"veo-3.1-fast-generate": { "audio": 0.15, "no_audio": 0.10 },
|
||||
"veo-3.1-generate": { "audio": 0.40, "no_audio": 0.20 }
|
||||
};
|
||||
$m := widgets.model;
|
||||
$r := widgets.resolution;
|
||||
$ga := widgets.generate_audio;
|
||||
$ga := (widgets.generate_audio = "true");
|
||||
$seconds := widgets.duration;
|
||||
$pps :=
|
||||
$contains($m, "lite")
|
||||
? ($r = "1080p" ? ($ga ? 0.08 : 0.05) : ($ga ? 0.05 : 0.03))
|
||||
: $contains($m, "fast")
|
||||
? ($r = "4k" ? ($ga ? 0.30 : 0.25) : $r = "1080p" ? ($ga ? 0.12 : 0.10) : ($ga ? 0.10 : 0.08))
|
||||
: ($r = "4k" ? ($ga ? 0.60 : 0.40) : ($ga ? 0.40 : 0.20));
|
||||
{"type":"usd","usd": $pps * $seconds}
|
||||
$modelKey :=
|
||||
$contains($m, "veo-3.1-fast-generate") ? "veo-3.1-fast-generate" :
|
||||
$contains($m, "veo-3.1-generate") ? "veo-3.1-generate" :
|
||||
"";
|
||||
$audioKey := $ga ? "audio" : "no_audio";
|
||||
$modelPrices := $lookup($prices, $modelKey);
|
||||
$pps := $lookup($modelPrices, $audioKey);
|
||||
($pps != null)
|
||||
? {"type":"usd","usd": $pps * $seconds}
|
||||
: {"type":"range_usd","min_usd": 0.4, "max_usd": 3.2}
|
||||
)
|
||||
""",
|
||||
),
|
||||
@@ -563,9 +482,6 @@ class Veo3FirstLastFrameNode(IO.ComfyNode):
|
||||
model: str,
|
||||
generate_audio: bool,
|
||||
):
|
||||
if "lite" in model and resolution == "4k":
|
||||
raise Exception("4K resolution is not supported by the veo-3.1-lite model.")
|
||||
|
||||
model = MODELS_MAP[model]
|
||||
initial_response = await sync_op(
|
||||
cls,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -80,7 +80,7 @@ class EmptyAceStepLatentAudio(io.ComfyNode):
|
||||
@classmethod
|
||||
def execute(cls, seconds, batch_size) -> io.NodeOutput:
|
||||
length = int(seconds * 44100 / 512 / 8)
|
||||
latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
|
||||
latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device())
|
||||
return io.NodeOutput({"samples": latent, "type": "audio"})
|
||||
|
||||
|
||||
@@ -103,7 +103,7 @@ class EmptyAceStep15LatentAudio(io.ComfyNode):
|
||||
@classmethod
|
||||
def execute(cls, seconds, batch_size) -> io.NodeOutput:
|
||||
length = round((seconds * 48000 / 1920))
|
||||
latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
|
||||
latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device())
|
||||
return io.NodeOutput({"samples": latent, "type": "audio"})
|
||||
|
||||
class ReferenceAudio(io.ComfyNode):
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import numpy as np
|
||||
|
||||
from comfy_api.latest import ComfyExtension, io
|
||||
from comfy_api.input import CurveInput
|
||||
from typing_extensions import override
|
||||
@@ -34,58 +32,10 @@ class CurveEditor(io.ComfyNode):
|
||||
return io.NodeOutput(result, ui=ui) if ui else io.NodeOutput(result)
|
||||
|
||||
|
||||
class ImageHistogram(io.ComfyNode):
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return io.Schema(
|
||||
node_id="ImageHistogram",
|
||||
display_name="Image Histogram",
|
||||
category="utils",
|
||||
inputs=[
|
||||
io.Image.Input("image"),
|
||||
],
|
||||
outputs=[
|
||||
io.Histogram.Output("rgb"),
|
||||
io.Histogram.Output("luminance"),
|
||||
io.Histogram.Output("red"),
|
||||
io.Histogram.Output("green"),
|
||||
io.Histogram.Output("blue"),
|
||||
],
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def execute(cls, image) -> io.NodeOutput:
|
||||
img = image[0].cpu().numpy()
|
||||
img_uint8 = np.clip(img * 255, 0, 255).astype(np.uint8)
|
||||
|
||||
def bincount(data):
|
||||
return np.bincount(data.ravel(), minlength=256)[:256]
|
||||
|
||||
hist_r = bincount(img_uint8[:, :, 0])
|
||||
hist_g = bincount(img_uint8[:, :, 1])
|
||||
hist_b = bincount(img_uint8[:, :, 2])
|
||||
|
||||
# Average of R, G, B histograms (same as Photoshop's RGB composite)
|
||||
rgb = ((hist_r + hist_g + hist_b) // 3).tolist()
|
||||
|
||||
# ITU-R BT.709-6, Item 3.2 (p.6) — Derivation of luminance signal
|
||||
# https://www.itu.int/rec/R-REC-BT.709-6-201506-I/en
|
||||
lum = 0.2126 * img[:, :, 0] + 0.7152 * img[:, :, 1] + 0.0722 * img[:, :, 2]
|
||||
luminance = bincount(np.clip(lum * 255, 0, 255).astype(np.uint8)).tolist()
|
||||
|
||||
return io.NodeOutput(
|
||||
rgb,
|
||||
luminance,
|
||||
hist_r.tolist(),
|
||||
hist_g.tolist(),
|
||||
hist_b.tolist(),
|
||||
)
|
||||
|
||||
|
||||
class CurveExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self):
|
||||
return [CurveEditor, ImageHistogram]
|
||||
return [CurveEditor]
|
||||
|
||||
|
||||
async def comfy_entrypoint():
|
||||
|
||||
@@ -991,6 +991,10 @@ async def validate_inputs(prompt_id, prompt, item, validated):
|
||||
|
||||
if isinstance(input_type, list) or input_type == io.Combo.io_type:
|
||||
if input_type == io.Combo.io_type:
|
||||
# Skip validation for combos with remote options — options
|
||||
# are fetched client-side and not available on the server.
|
||||
if extra_info.get("remote"):
|
||||
continue
|
||||
combo_options = extra_info.get("options", [])
|
||||
else:
|
||||
combo_options = input_type
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
comfyui-frontend-package==1.42.8
|
||||
comfyui-workflow-templates==0.9.44
|
||||
comfyui-workflow-templates==0.9.39
|
||||
comfyui-embedded-docs==0.4.3
|
||||
torch
|
||||
torchsde
|
||||
|
||||
@@ -146,10 +146,6 @@ def is_loopback(host):
|
||||
def create_origin_only_middleware():
|
||||
@web.middleware
|
||||
async def origin_only_middleware(request: web.Request, handler):
|
||||
if 'Sec-Fetch-Site' in request.headers:
|
||||
sec_fetch_site = request.headers['Sec-Fetch-Site']
|
||||
if sec_fetch_site == 'cross-site':
|
||||
return web.Response(status=403)
|
||||
#this code is used to prevent the case where a random website can queue comfy workflows by making a POST to 127.0.0.1 which browsers don't prevent for some dumb reason.
|
||||
#in that case the Host and Origin hostnames won't match
|
||||
#I know the proper fix would be to add a cookie but this should take care of the problem in the meantime
|
||||
|
||||
Reference in New Issue
Block a user