wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-28 01:47:32 +08:00
Code Issues Actions 29 Packages Projects Releases Wiki Activity

Update categories and add new blueprints

Browse Source
This commit is contained in:
ComfyUI Wiki 2026-05-25 18:01:48 +08:00
parent 1c8d4ca092
commit 577c56bb6b
24 changed files with 2370 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
blueprints/Canny to Image (Z-Image-Turbo).json
View File

@ -1553,7 +1553,7 @@
"VHS_MetadataImage": true, "VHS_MetadataImage": true,
"VHS_KeepIntermediate": true "VHS_KeepIntermediate": true
}, },
"category": "Image generation and editing/Canny to image", "category": "Image generation and editing/Conditioned",
"description": "Generates an image from a Canny edge map using Z-Image-Turbo, with text conditioning." "description": "Generates an image from a Canny edge map using Z-Image-Turbo, with text conditioning."
} }
] ]

2
blueprints/Canny to Video (LTX 2.0).json
View File

@ -3600,7 +3600,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Video generation and editing/Canny to video", "category": "Video generation and editing/Conditioned",
"description": "Generates video from Canny edge maps using LTX-2, with optional synchronized audio." "description": "Generates video from Canny edge maps using LTX-2, with optional synchronized audio."
} }
] ]

2
blueprints/ControlNet (Z-Image-Turbo).json
View File

@ -1401,7 +1401,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Image generation and editing/ControlNet", "category": "Image generation and editing/Conditioned",
"description": "Generates images from a text prompt and ControlNet conditioning (e.g. depth, canny) using Z-Image-Turbo." "description": "Generates images from a text prompt and ControlNet conditioning (e.g. depth, canny) using Z-Image-Turbo."
} }
] ]

2
blueprints/Depth to Image (Z-Image-Turbo).json
View File

@ -1579,7 +1579,7 @@
"VHS_MetadataImage": true, "VHS_MetadataImage": true,
"VHS_KeepIntermediate": true "VHS_KeepIntermediate": true
}, },
"category": "Image generation and editing/Depth to image", "category": "Image generation and editing/Conditioned",
"description": "Generates an image from a depth map using Z-Image-Turbo with text conditioning." "description": "Generates an image from a depth map using Z-Image-Turbo with text conditioning."
}, },
{ {

5
blueprints/Depth to Video (ltx 2.0).json
View File

@ -4233,7 +4233,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Video generation and editing/Depth to video", "category": "Video generation and editing/Conditioned",
"description": "Generates depth-controlled video with LTX-2: motion and structure follow a depth-reference video alongside text prompting, optional first-frame image conditioning, with optional synchronized audio." "description": "Generates depth-controlled video with LTX-2: motion and structure follow a depth-reference video alongside text prompting, optional first-frame image conditioning, with optional synchronized audio."
}, },
{ {
@ -5194,8 +5194,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model.", "description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
"category": "Video generation and editing/Depth to video"
} }
] ]
}, },

2
blueprints/First-Last-Frame to Video (LTX-2.3).json
View File

@ -3350,7 +3350,7 @@
} }
], ],
"extra": {}, "extra": {},
"category": "Video generation and editing/First-Last-Frame to Video", "category": "Video generation and editing/Conditioned",
"description": "Generates a video interpolating between first and last keyframes using LTX-2.3." "description": "Generates a video interpolating between first and last keyframes using LTX-2.3."
} }
] ]

2
blueprints/First-Last-Frame to Video.json
View File

@ -3350,7 +3350,7 @@
} }
], ],
"extra": {}, "extra": {},
"category": "Video generation and editing/First-Last-Frame to Video", "category": "Video generation and editing/FLF2V",
"description": "Generates a video that interpolates between the first and last keyframes using LTX-2.3, including optional audio." "description": "Generates a video that interpolates between the first and last keyframes using LTX-2.3, including optional audio."
} }
] ]

2
blueprints/Geometry Estimation (MoGe).json
View File

@ -1256,6 +1256,8 @@
"type": "BOOLEAN" "type": "BOOLEAN"
} }
], ],
"category": "3D/Geometry Estimation",
"description": "Estimates 3D scene geometry from an input image using MoGe, outputting a mesh plus OpenGL and DirectX normal maps.",
"extra": {} "extra": {}
} }
] ]

2
blueprints/Image Captioning (gemini).json
View File

@ -310,7 +310,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Text generation/Image Captioning", "category": "Image Tools",
"description": "Generates descriptive captions for images using Google's Gemini multimodal LLM." "description": "Generates descriptive captions for images using Google's Gemini multimodal LLM."
} }
] ]

9
blueprints/Depth Estimation (MoGe).json → blueprints/Image Depth Estimation (MoGe).json
View File

@ -15,7 +15,7 @@
330 330
], ],
"flags": {}, "flags": {},
"order": 3, "order": 0,
"mode": 0, "mode": 0,
"inputs": [ "inputs": [
{ {
@ -80,6 +80,7 @@
"links": [] "links": []
} }
], ],
"title": "Image Depth Estimation (MoGe)",
"properties": { "properties": {
"proxyWidgets": [ "proxyWidgets": [
[ [
@ -109,8 +110,7 @@
"secondTabOffset": 80, "secondTabOffset": 80,
"secondTabWidth": 65 "secondTabWidth": 65
}, },
"widgets_values": [], "widgets_values": []
"title": "Depth Estimation (MoGe)"
} }
], ],
"links": [], "links": [],
@ -128,7 +128,8 @@
}, },
"revision": 0, "revision": 0,
"config": {}, "config": {},
"name": "Depth Estimation (MoGe)", "name": "Image Depth Estimation (MoGe)",
"description": "Estimates monocular depth from an input image using MoGe, outputting both raw and colorized depth maps plus a mask.",
"inputNode": { "inputNode": {
"id": -10, "id": -10,
"bounding": [ "bounding": [

12
blueprints/Face Detection (Mediapipe).json → blueprints/Image Face Detection (Mediapipe).json
View File

@ -15,7 +15,7 @@
400 400
], ],
"flags": {}, "flags": {},
"order": 3, "order": 0,
"mode": 0, "mode": 0,
"inputs": [ "inputs": [
{ {
@ -119,6 +119,7 @@
"links": [] "links": []
} }
], ],
"title": "Image Face Detection (Mediapipe)",
"properties": { "properties": {
"proxyWidgets": [ "proxyWidgets": [
[ [
@ -164,8 +165,7 @@
"secondTabOffset": 80, "secondTabOffset": 80,
"secondTabWidth": 65 "secondTabWidth": 65
}, },
"widgets_values": [], "widgets_values": []
"title": "Face Detection (Mediapipe)"
} }
], ],
"links": [], "links": [],
@ -183,7 +183,8 @@
}, },
"revision": 0, "revision": 0,
"config": {}, "config": {},
"name": "Face Detection (Mediapipe)", "name": "Image Face Detection (Mediapipe)",
"description": "Detects facial landmarks from an image using MediaPipe, outputting landmark data, face bounding boxes, and an optional face-region mask.",
"inputNode": { "inputNode": {
"id": -10, "id": -10,
"bounding": [ "bounding": [
@ -769,7 +770,8 @@
"type": "COMBO" "type": "COMBO"
} }
], ],
"extra": {} "extra": {},
"category": "Conditioning & Preprocessors/Face Detection"
} }
] ]
}, },

2
blueprints/Image Segmentation (SAM3).json
View File

@ -703,7 +703,7 @@
} }
], ],
"extra": {}, "extra": {},
"category": "Image Tools/Image Segmentation", "category": "Conditioning & Preprocessors/Segmentation & Mask",
"description": "Segments images into masks using Meta SAM3 from text prompts, points, or boxes." "description": "Segments images into masks using Meta SAM3 from text prompts, points, or boxes."
} }
] ]

2
blueprints/Image to Depth Map (Lotus).json
View File

@ -948,7 +948,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Image Tools/Preprocessors", "category": "Conditioning & Preprocessors/Depth",
"description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model." "description": "Estimates a monocular depth map from an input image using the Lotus depth estimation model."
} }
] ]

2
blueprints/Image to Pose Map (SDPose Multi-Person).json
View File

@ -1197,7 +1197,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Image Tools/Preprocessors", "category": "Conditioning & Preprocessors/Pose",
"description": "Detects multiple people in an image and outputs per-person pose keypoints, skeleton renders, and bounding boxes using SDPose." "description": "Detects multiple people in an image and outputs per-person pose keypoints, skeleton renders, and bounding boxes using SDPose."
} }
] ]

2
blueprints/Image to Pose Map (SDPose-OOD).json
View File

@ -877,7 +877,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Image Tools/Preprocessors", "category": "Conditioning & Preprocessors/Pose",
"description": "Extracts human pose keypoints and stick-figure visuals from an image using SDPose-OOD, with optional bounding-box input per subject." "description": "Extracts human pose keypoints and stick-figure visuals from an image using SDPose-OOD, with optional bounding-box input per subject."
} }
] ]

2
blueprints/Pose to Image (Z-Image-Turbo).json
View File

@ -1298,7 +1298,7 @@
"VHS_MetadataImage": true, "VHS_MetadataImage": true,
"VHS_KeepIntermediate": true "VHS_KeepIntermediate": true
}, },
"category": "Image generation and editing/Pose to image", "category": "Image generation and editing/Conditioned",
"description": "Generates an image from pose keypoints using Z-Image-Turbo with text conditioning." "description": "Generates an image from pose keypoints using Z-Image-Turbo with text conditioning."
} }
] ]

2
blueprints/Pose to Video (LTX 2.0).json
View File

@ -3870,7 +3870,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Video generation and editing/Pose to video", "category": "Video generation and editing/Conditioned",
"description": "Generates video from pose reference frames using LTX-2, with optional synchronized audio." "description": "Generates video from pose reference frames using LTX-2, with optional synchronized audio."
} }
] ]

2
blueprints/Prompt Enhance.json
View File

@ -270,7 +270,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Text generation/Prompt enhance", "category": "Text Tools",
"description": "Expands short text prompts into detailed descriptions using a text generation model for better generation quality." "description": "Expands short text prompts into detailed descriptions using a text generation model for better generation quality."
} }
] ]

2
blueprints/Video Captioning (Gemini).json
View File

@ -307,7 +307,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Text generation/Video Captioning", "category": "Video Tools",
"description": "Generates descriptive captions for video input using Google's Gemini multimodal LLM." "description": "Generates descriptive captions for video input using Google's Gemini multimodal LLM."
} }
] ]

1225
blueprints/Video Depth Estimation (MoGe).json Normal file
View File

File diff suppressed because it is too large Load Diff

1109
blueprints/Video Face Detection (Mediapipe).json Normal file
View File

File diff suppressed because it is too large Load Diff

2
blueprints/Video Inpaint (VOID).json
View File

@ -3768,7 +3768,7 @@
} }
], ],
"extra": {}, "extra": {},
"category": "Video Tools", "category": "Video generation and editing/Inpaint video",
"description": "Removes objects from video by inpainting masked regions using VOID (CogVideoX), with SAM3 text-guided segmentation and optional two-pass optical-flow refinement." "description": "Removes objects from video by inpainting masked regions using VOID (CogVideoX), with SAM3 text-guided segmentation and optional two-pass optical-flow refinement."
}, },
{ {

2
blueprints/Video Segmentation (SAM3).json
View File

@ -818,7 +818,7 @@
} }
], ],
"extra": {}, "extra": {},
"category": "Video Tools", "category": "Conditioning & Preprocessors/Segmentation & Mask",
"description": "Segments video into temporally consistent masks using Meta SAM3 from text or interactive prompts." "description": "Segments video into temporally consistent masks using Meta SAM3 from text or interactive prompts."
} }
] ]

2
blueprints/Video to Pose Map (SDPose Multi-Person).json
View File

@ -1314,7 +1314,7 @@
"extra": { "extra": {
"workflowRendererVersion": "LG" "workflowRendererVersion": "LG"
}, },
"category": "Video Tools", "category": "Conditioning & Preprocessors/Pose",
"description": "Extracts multi-person pose keypoints and skeleton frame sequences from video using SDPose with built-in person detection." "description": "Extracts multi-person pose keypoints and skeleton frame sequences from video using SDPose with built-in person detection."
} }
] ]