ComfyUI/blueprints/Video Segmentation (SAM3).json
Daxiong (Lin) 04879a8113
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Build package / Build Test (3.10) (push) Waiting to run
Build package / Build Test (3.11) (push) Waiting to run
Build package / Build Test (3.12) (push) Waiting to run
Build package / Build Test (3.13) (push) Waiting to run
Build package / Build Test (3.14) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
Add new open-source model and built-in tool blueprints (#13980)
2026-05-25 12:25:16 -07:00

828 lines
20 KiB
JSON

{
"revision": 0,
"last_node_id": 130,
"last_link_id": 0,
"nodes": [
{
"id": 130,
"type": "7937cf78-b52b-40a3-93b2-b4e2e5f98df1",
"pos": [
-1210,
-2780
],
"size": [
300,
370
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": null
},
{
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": null
},
{
"name": "bboxes",
"type": "BOUNDING_BOX",
"link": null
},
{
"name": "positive_coords",
"type": "STRING",
"link": null
},
{
"name": "negative_coords",
"type": "STRING",
"link": null
},
{
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": null
},
{
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": null
},
{
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": null
},
{
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": []
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": []
},
{
"name": "audio",
"type": "AUDIO",
"links": null
},
{
"name": "fps",
"type": "FLOAT",
"links": null
}
],
"properties": {
"proxyWidgets": [
[
"125",
"text"
],
[
"126",
"threshold"
],
[
"126",
"refine_iterations"
],
[
"126",
"individual_masks"
],
[
"127",
"ckpt_name"
]
],
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [],
"title": "Video Segmentation (SAM3)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "7937cf78-b52b-40a3-93b2-b4e2e5f98df1",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 130,
"lastLinkId": 299,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Video Segmentation (SAM3)",
"inputNode": {
"id": -10,
"bounding": [
-2260,
-3450,
136.369140625,
220
]
},
"outputNode": {
"id": -20,
"bounding": [
-1050,
-3510,
120,
120
]
},
"inputs": [
{
"id": "680ffd88-32fe-48be-88d6-91ea44d5eaee",
"name": "video",
"type": "VIDEO",
"linkIds": [
252
],
"pos": [
-2143.630859375,
-3430
]
},
{
"id": "ceaf249c-32d7-4624-8bf6-e590e347ed90",
"name": "text",
"type": "STRING",
"linkIds": [
254
],
"pos": [
-2143.630859375,
-3410
]
},
{
"id": "1ffbff36-da0c-4854-8cb4-88ad31e64f99",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
255
],
"pos": [
-2143.630859375,
-3390
]
},
{
"id": "67b7f4c7-cec0-4e00-b154-23cc1abf880e",
"name": "positive_coords",
"type": "STRING",
"linkIds": [
256
],
"pos": [
-2143.630859375,
-3370
]
},
{
"id": "b090a498-2bde-46b9-9554-18501401d687",
"name": "negative_coords",
"type": "STRING",
"linkIds": [
257
],
"pos": [
-2143.630859375,
-3350
]
},
{
"id": "1a76dfcf-ce95-46af-bba5-c42160c683dd",
"name": "threshold",
"type": "FLOAT",
"linkIds": [
261
],
"pos": [
-2143.630859375,
-3330
]
},
{
"id": "999523fa-c476-4c53-80c3-0a2f554d18ab",
"name": "refine_iterations",
"type": "INT",
"linkIds": [
262
],
"pos": [
-2143.630859375,
-3310
]
},
{
"id": "d2371011-7fe5-4a39-b0c1-df2e0bbd6ece",
"name": "individual_masks",
"type": "BOOLEAN",
"linkIds": [
263
],
"pos": [
-2143.630859375,
-3290
]
},
{
"id": "675a8b37-17db-48d1-853c-2fe5d6a74582",
"name": "ckpt_name",
"type": "COMBO",
"linkIds": [
273
],
"pos": [
-2143.630859375,
-3270
]
}
],
"outputs": [
{
"id": "ff50da09-1e59-4a58-9b7f-be1a00aa5913",
"name": "masks",
"type": "MASK",
"linkIds": [
231
],
"localized_name": "masks",
"pos": [
-1030,
-3490
]
},
{
"id": "8f622e40-8528-4078-b7d3-147e9f872194",
"name": "bboxes",
"type": "BOUNDING_BOX",
"linkIds": [
232
],
"localized_name": "bboxes",
"pos": [
-1030,
-3470
]
},
{
"id": "6c9924ec-f0fa-4509-83ea-8f97f5889bcc",
"name": "audio",
"type": "AUDIO",
"linkIds": [
259
],
"pos": [
-1030,
-3450
]
},
{
"id": "82c1cddc-ab11-44eb-9e2f-1a5c7ea5645b",
"name": "fps",
"type": "FLOAT",
"linkIds": [
260
],
"pos": [
-1030,
-3430
]
}
],
"widgets": [],
"nodes": [
{
"id": 125,
"type": "CLIPTextEncode",
"pos": [
-2010,
-3040
],
"size": [
400,
200
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 240
},
{
"localized_name": "text",
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 254
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
200
]
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
""
]
},
{
"id": 126,
"type": "SAM3_Detect",
"pos": [
-1520,
-3520
],
"size": [
270,
290
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"label": "model",
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 237
},
{
"label": "image",
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 253
},
{
"label": "conditioning",
"localized_name": "conditioning",
"name": "conditioning",
"shape": 7,
"type": "CONDITIONING",
"link": 200
},
{
"label": "bboxes",
"localized_name": "bboxes",
"name": "bboxes",
"shape": 7,
"type": "BOUNDING_BOX",
"link": 255
},
{
"label": "positive_coords",
"localized_name": "positive_coords",
"name": "positive_coords",
"shape": 7,
"type": "STRING",
"link": 256
},
{
"label": "negative_coords",
"localized_name": "negative_coords",
"name": "negative_coords",
"shape": 7,
"type": "STRING",
"link": 257
},
{
"localized_name": "threshold",
"name": "threshold",
"type": "FLOAT",
"widget": {
"name": "threshold"
},
"link": 261
},
{
"localized_name": "refine_iterations",
"name": "refine_iterations",
"type": "INT",
"widget": {
"name": "refine_iterations"
},
"link": 262
},
{
"localized_name": "individual_masks",
"name": "individual_masks",
"type": "BOOLEAN",
"widget": {
"name": "individual_masks"
},
"link": 263
}
],
"outputs": [
{
"localized_name": "masks",
"name": "masks",
"type": "MASK",
"links": [
231
]
},
{
"localized_name": "bboxes",
"name": "bboxes",
"type": "BOUNDING_BOX",
"links": [
232
]
}
],
"properties": {
"Node name for S&R": "SAM3_Detect",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
},
"widgets_values": [
0.5,
2,
false
]
},
{
"id": 127,
"type": "CheckpointLoaderSimple",
"pos": [
-1970,
-3310
],
"size": [
330,
160
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "ckpt_name",
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": 273
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"links": [
237
]
},
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"links": [
240
]
},
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": null
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65,
"models": [
{
"name": "sam3.1_multiplex_fp16.safetensors",
"url": "https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors",
"directory": "checkpoints"
}
]
},
"widgets_values": [
"sam3.1_multiplex_fp16.safetensors"
]
},
{
"id": 128,
"type": "GetVideoComponents",
"pos": [
-1910,
-3540
],
"size": [
230,
120
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": 252
}
],
"outputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": [
253
]
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
259
]
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"links": [
260
]
}
],
"properties": {
"Node name for S&R": "GetVideoComponents",
"cnr_id": "comfy-core",
"ver": "0.19.3",
"enableTabs": false,
"tabWidth": 65,
"tabXOffset": 10,
"hasSecondTab": false,
"secondTabText": "Send Back",
"secondTabOffset": 80,
"secondTabWidth": 65
}
},
{
"id": 129,
"type": "Note",
"pos": [
-1980,
-2790
],
"size": [
370,
250
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: Prompt format",
"properties": {},
"widgets_values": [
"Max tokens for this model is only 32, to separately prompt multiple subjects you can separate prompts with comma, and set the max amount of objects detected for each prompt with :N\n\nFor example above test prompt finds 2 cakes, one apron, 4 window panels"
],
"color": "#432",
"bgcolor": "#653"
}
],
"groups": [],
"links": [
{
"id": 237,
"origin_id": 127,
"origin_slot": 0,
"target_id": 126,
"target_slot": 0,
"type": "MODEL"
},
{
"id": 200,
"origin_id": 125,
"origin_slot": 0,
"target_id": 126,
"target_slot": 2,
"type": "CONDITIONING"
},
{
"id": 240,
"origin_id": 127,
"origin_slot": 1,
"target_id": 125,
"target_slot": 0,
"type": "CLIP"
},
{
"id": 231,
"origin_id": 126,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "MASK"
},
{
"id": 232,
"origin_id": 126,
"origin_slot": 1,
"target_id": -20,
"target_slot": 1,
"type": "BOUNDING_BOX"
},
{
"id": 252,
"origin_id": -10,
"origin_slot": 0,
"target_id": 128,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 253,
"origin_id": 128,
"origin_slot": 0,
"target_id": 126,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 254,
"origin_id": -10,
"origin_slot": 1,
"target_id": 125,
"target_slot": 1,
"type": "STRING"
},
{
"id": 255,
"origin_id": -10,
"origin_slot": 2,
"target_id": 126,
"target_slot": 3,
"type": "BOUNDING_BOX"
},
{
"id": 256,
"origin_id": -10,
"origin_slot": 3,
"target_id": 126,
"target_slot": 4,
"type": "STRING"
},
{
"id": 257,
"origin_id": -10,
"origin_slot": 4,
"target_id": 126,
"target_slot": 5,
"type": "STRING"
},
{
"id": 259,
"origin_id": 128,
"origin_slot": 1,
"target_id": -20,
"target_slot": 2,
"type": "AUDIO"
},
{
"id": 260,
"origin_id": 128,
"origin_slot": 2,
"target_id": -20,
"target_slot": 3,
"type": "FLOAT"
},
{
"id": 261,
"origin_id": -10,
"origin_slot": 5,
"target_id": 126,
"target_slot": 6,
"type": "FLOAT"
},
{
"id": 262,
"origin_id": -10,
"origin_slot": 6,
"target_id": 126,
"target_slot": 7,
"type": "INT"
},
{
"id": 263,
"origin_id": -10,
"origin_slot": 7,
"target_id": 126,
"target_slot": 8,
"type": "BOOLEAN"
},
{
"id": 273,
"origin_id": -10,
"origin_slot": 8,
"target_id": 127,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {},
"category": "Conditioning & Preprocessors/Segmentation & Mask",
"description": "Segments video into temporally consistent masks using Meta SAM3 from text or interactive prompts."
}
]
},
"extra": {}
}