wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-06-19 14:29:33 +08:00
Code Issues Actions 27 Packages Projects Releases Wiki Activity
52257bb435
ComfyUI/blueprints/Image Depth Estimation (Depth Anything 3).json
Daxiong (Lin) c44d261fc2
Add new model blueprints (#14506)
2026-06-17 08:52:55 +08:00

569 lines
14 KiB
JSON
Raw Blame History

{
"revision": 0,
"last_node_id": 89,
"last_link_id": 0,
"nodes": [
{
"id": 89,
"type": "85e595bd-af9e-40ee-85c5-b98bb15da47a",
"pos": [
320,
520
],
"size": [
400,
360
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": null
},
{
"name": "resolution",
"type": "INT",
"widget": {
"name": "resolution"
},
"link": null
},
{
"name": "resize_method",
"type": "COMBO",
"widget": {
"name": "resize_method"
},
"link": null
},
{
"label": "output_type",
"name": "output",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "output"
},
"link": null
},
{
"label": "output_normalization",
"name": "output.normalization",
"type": "COMBO",
"widget": {
"name": "output.normalization"
},
"link": null
},
{
"label": "apply_sky_clip",
"name": "output.apply_sky_clip",
"type": "BOOLEAN",
"widget": {
"name": "output.apply_sky_clip"
},
"link": null
},
{
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": []
}
],
"properties": {
"proxyWidgets": [
[
"87",
"resolution"
],
[
"87",
"resize_method"
],
[
"86",
"output"
],
[
"86",
"output.normalization"
],
[
"86",
"output.apply_sky_clip"
],
[
"88",
"model_name"
]
],
"cnr_id": "comfy-core",
"ver": "0.24.0"
},
"widgets_values": [],
"title": "Image Depth Estimation (Depth Anything 3)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "85e595bd-af9e-40ee-85c5-b98bb15da47a",
"version": 1,
"state": {
"lastGroupId": 4,
"lastNodeId": 89,
"lastLinkId": 109,
"lastRerouteId": 0
},
"revision": 2,
"config": {},
"name": "Image Depth Estimation (Depth Anything 3)",
"inputNode": {
"id": -10,
"bounding": [
400,
90,
166.998046875,
188
]
},
"outputNode": {
"id": -20,
"bounding": [
1250,
146,
128,
68
]
},
"inputs": [
{
"id": "43cf3118-495a-487d-8eb3-a17c7e92f64f",
"name": "image",
"type": "IMAGE",
"linkIds": [
19
],
"localized_name": "image",
"pos": [
542.998046875,
114
]
},
{
"id": "1089a0a1-6db1-45a8-84b0-0bfdc2ed920a",
"name": "resolution",
"type": "INT",
"linkIds": [
22
],
"pos": [
542.998046875,
134
]
},
{
"id": "25fb64ac-26d5-466d-995b-6d51b9afa2c4",
"name": "resize_method",
"type": "COMBO",
"linkIds": [
23
],
"pos": [
542.998046875,
154
]
},
{
"id": "8acafb7c-6c8b-46b3-9d74-c563498a3af1",
"name": "output",
"type": "COMFY_DYNAMICCOMBO_V3",
"linkIds": [
24
],
"label": "output_type",
"pos": [
542.998046875,
174
]
},
{
"id": "1da5009b-4648-43e8-a257-16426630cf22",
"name": "output.normalization",
"type": "COMBO",
"linkIds": [
25
],
"label": "output_normalization",
"pos": [
542.998046875,
194
]
},
{
"id": "fd7edb33-5fb1-4538-a411-26e5039a9321",
"name": "output.apply_sky_clip",
"type": "BOOLEAN",
"linkIds": [
26
],
"label": "apply_sky_clip",
"pos": [
542.998046875,
214
]
},
{
"id": "b5be4c8a-b833-4f1e-8c94-3ed1dd722190",
"name": "model_name",
"type": "COMBO",
"linkIds": [
106
],
"pos": [
542.998046875,
234
]
}
],
"outputs": [
{
"id": "478ab537-63bc-4d74-a9f0-c975f550880f",
"name": "IMAGE",
"type": "IMAGE",
"linkIds": [
7
],
"localized_name": "IMAGE",
"pos": [
1274,
170
]
}
],
"widgets": [],
"nodes": [
{
"id": 86,
"type": "DA3Render",
"pos": [
800,
310
],
"size": [
380,
130
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "da3_geometry",
"name": "da3_geometry",
"type": "DA3_GEOMETRY",
"link": 12
},
{
"localized_name": "output",
"name": "output",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "output"
},
"link": 24
},
{
"localized_name": "output.normalization",
"name": "output.normalization",
"type": "COMBO",
"widget": {
"name": "output.normalization"
},
"link": 25
},
{
"localized_name": "output.apply_sky_clip",
"name": "output.apply_sky_clip",
"type": "BOOLEAN",
"widget": {
"name": "output.apply_sky_clip"
},
"link": 26
},
{
"name": "geometry",
"type": "DA3_GEOMETRY",
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
7
]
}
],
"properties": {
"Node name for S&R": "DA3Render",
"cnr_id": "comfy-core",
"ver": "0.19.0"
},
"widgets_values": [
"depth",
"v2_style",
false
]
},
{
"id": 87,
"type": "DA3Inference",
"pos": [
800,
50
],
"size": [
390,
130
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "da3_model",
"name": "da3_model",
"type": "DA3_MODEL",
"link": 107
},
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 19
},
{
"localized_name": "resolution",
"name": "resolution",
"type": "INT",
"widget": {
"name": "resolution"
},
"link": 22
},
{
"localized_name": "resize_method",
"name": "resize_method",
"type": "COMBO",
"widget": {
"name": "resize_method"
},
"link": 23
},
{
"localized_name": "mode",
"name": "mode",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "mode"
},
"link": null
}
],
"outputs": [
{
"localized_name": "da3_geometry",
"name": "da3_geometry",
"type": "DA3_GEOMETRY",
"slot_index": 0,
"links": [
12
]
}
],
"properties": {
"Node name for S&R": "DA3Inference",
"cnr_id": "comfy-core",
"ver": "0.19.0"
},
"widgets_values": [
504,
"upper_bound_resize",
"mono"
]
},
{
"id": 88,
"type": "LoadDA3Model",
"pos": [
810,
-160
],
"size": [
400,
140
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": 106
},
{
"localized_name": "weight_dtype",
"name": "weight_dtype",
"type": "COMBO",
"widget": {
"name": "weight_dtype"
},
"link": null
}
],
"outputs": [
{
"localized_name": "DA3_MODEL",
"name": "DA3_MODEL",
"type": "DA3_MODEL",
"links": [
107
]
}
],
"properties": {
"Node name for S&R": "LoadDA3Model",
"cnr_id": "comfy-core",
"ver": "0.24.0",
"models": [
{
"name": "depth_anything_3_mono_large.safetensors",
"url": "https://huggingface.co/Comfy-Org/Depth-Anything-3/resolve/main/geometry_estimation/depth_anything_3_mono_large.safetensors",
"directory": "geometry_estimation"
}
]
},
"widgets_values": [
"depth_anything_3_mono_large.safetensors",
"default"
]
}
],
"groups": [],
"links": [
{
"id": 12,
"origin_id": 87,
"origin_slot": 0,
"target_id": 86,
"target_slot": 0,
"type": "DA3_GEOMETRY"
},
{
"id": 19,
"origin_id": -10,
"origin_slot": 0,
"target_id": 87,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 7,
"origin_id": 86,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 22,
"origin_id": -10,
"origin_slot": 1,
"target_id": 87,
"target_slot": 2,
"type": "INT"
},
{
"id": 23,
"origin_id": -10,
"origin_slot": 2,
"target_id": 87,
"target_slot": 3,
"type": "COMBO"
},
{
"id": 24,
"origin_id": -10,
"origin_slot": 3,
"target_id": 86,
"target_slot": 1,
"type": "COMFY_DYNAMICCOMBO_V3"
},
{
"id": 25,
"origin_id": -10,
"origin_slot": 4,
"target_id": 86,
"target_slot": 2,
"type": "COMBO"
},
{
"id": 26,
"origin_id": -10,
"origin_slot": 5,
"target_id": 86,
"target_slot": 3,
"type": "BOOLEAN"
},
{
"id": 106,
"origin_id": -10,
"origin_slot": 6,
"target_id": 88,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 107,
"origin_id": 88,
"origin_slot": 0,
"target_id": 87,
"target_slot": 0,
"type": "DA3_MODEL"
}
],
"extra": {},
"category": "Conditioning & Preprocessors/Depth",
"description": "This subgraph takes an input image and produces a depth map using the Depth Anything 3 model, which recovers spatially consistent geometry from any number of views. It is ideal for single or multi-view images, videos, and 3D scenes where accurate depth estimation is needed for tasks like SLAM, novel view synthesis, or spatial perception. The model uses a plain transformer backbone and supports both monocular and multi-view inputs without."
}
]
},
"extra": {
"BlueprintDescription": "This subgraph takes an input image and produces a depth map using the Depth Anything 3 model, which recovers spatially consistent geometry from any number of views. It is ideal for single or multi-view images, videos, and 3D scenes where accurate depth estimation is needed for tasks like SLAM, novel view synthesis, or spatial perception. The model uses a plain transformer backbone and supports both monocular and multi-view inputs without."
}
}
Reference in New Issue View Git Blame Copy Permalink