comfy-anything / workflows /sdxl-segmentanything-groundingdino.json
martintomov's picture
workflows
6286aa4 verified
{
"last_node_id": 30,
"last_link_id": 48,
"nodes": [
{
"id": 6,
"type": "EmptyLatentImage",
"pos": [
1890,
1302
],
"size": {
"0": 315,
"1": 106
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
8
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
1024,
1024,
1
]
},
{
"id": 3,
"type": "KSampler",
"pos": [
2339,
727
],
"size": {
"0": 315,
"1": 262
},
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 42
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 15
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 6
},
{
"name": "latent_image",
"type": "LATENT",
"link": 8
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
26
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
808794406550722,
"randomize",
4,
1,
"dpmpp_2m_sde",
"sgm_uniform",
1
]
},
{
"id": 25,
"type": "PreviewImage",
"pos": [
3013.8057969602296,
1050.9954701696279
],
"size": {
"0": 608.9395141601562,
"1": 627.6407470703125
},
"flags": {},
"order": 21,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 28
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 23,
"type": "Image Blend by Mask",
"pos": [
2580,
1568
],
"size": {
"0": 315,
"1": 98
},
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "image_a",
"type": "IMAGE",
"link": 29
},
{
"name": "image_b",
"type": "IMAGE",
"link": 47
},
{
"name": "mask",
"type": "IMAGE",
"link": 31
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
32
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "Image Blend by Mask"
},
"widgets_values": [
1
]
},
{
"id": 27,
"type": "Note",
"pos": [
2263,
431
],
"size": {
"0": 295.87030029296875,
"1": 58
},
"flags": {},
"order": 1,
"mode": 0,
"properties": {
"text": ""
},
"widgets_values": [
"disable ipadapter to increase speed"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 24,
"type": "VAEDecode",
"pos": [
2699,
1004
],
"size": {
"0": 210,
"1": 46
},
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 26
},
{
"name": "vae",
"type": "VAE",
"link": 27
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
28,
29
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
}
},
{
"id": 14,
"type": "ImageResize+",
"pos": [
1405,
1454
],
"size": {
"0": 315,
"1": 218
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 34
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
18,
45
],
"shape": 3,
"slot_index": 0
},
{
"name": "width",
"type": "INT",
"links": null,
"shape": 3
},
{
"name": "height",
"type": "INT",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "ImageResize+"
},
"widgets_values": [
1024,
1024,
"nearest",
false,
"always",
0
]
},
{
"id": 8,
"type": "IPAdapterAdvanced",
"pos": [
1891,
427
],
"size": {
"0": 315,
"1": 278
},
"flags": {},
"order": 9,
"mode": 4,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 10
},
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": 11
},
{
"name": "image",
"type": "IMAGE",
"link": null
},
{
"name": "image_negative",
"type": "IMAGE",
"link": null
},
{
"name": "attn_mask",
"type": "MASK",
"link": null
},
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": null
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "IPAdapterAdvanced"
},
"widgets_values": [
0.3,
"ease in-out",
"concat",
0,
1,
"V only"
]
},
{
"id": 21,
"type": "MaskToImage",
"pos": [
2322,
1891
],
"size": {
"0": 210,
"1": 26
},
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "mask",
"type": "MASK",
"link": 46
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
25,
31
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "MaskToImage"
}
},
{
"id": 9,
"type": "IPAdapterUnifiedLoader",
"pos": [
1884,
253
],
"size": {
"0": 315,
"1": 78
},
"flags": {},
"order": 2,
"mode": 4,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": null
},
{
"name": "ipadapter",
"type": "IPADAPTER",
"link": null
}
],
"outputs": [
{
"name": "model",
"type": "MODEL",
"links": [
10
],
"shape": 3,
"slot_index": 0
},
{
"name": "ipadapter",
"type": "IPADAPTER",
"links": [
11
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "IPAdapterUnifiedLoader"
},
"widgets_values": [
"VIT-G (medium strength)"
]
},
{
"id": 26,
"type": "PreviewImage",
"pos": [
3711,
1056
],
"size": {
"0": 638.635986328125,
"1": 626.17138671875
},
"flags": {},
"order": 23,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 32
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 12,
"type": "ControlNetLoader",
"pos": [
1890,
1488
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "CONTROL_NET",
"type": "CONTROL_NET",
"links": [
16
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "ControlNetLoader"
},
"widgets_values": [
"control-lora-depth-rank128.safetensors"
]
},
{
"id": 11,
"type": "ControlNetApply",
"pos": [
1886,
1621
],
"size": {
"0": 317.4000244140625,
"1": 98
},
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 14
},
{
"name": "control_net",
"type": "CONTROL_NET",
"link": 16,
"slot_index": 1
},
{
"name": "image",
"type": "IMAGE",
"link": 19
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
15
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "ControlNetApply"
},
"widgets_values": [
1
]
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [
1404,
934
],
"size": {
"0": 315,
"1": 98
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
42
],
"shape": 3,
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
43,
44
],
"shape": 3,
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": [
27
],
"shape": 3,
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"Juggernaut_X_RunDiffusion_Hyper.safetensors"
]
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
1846,
1054
],
"size": {
"0": 400,
"1": 200
},
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 44
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
6
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"illustration, anime, naked, nsfw"
]
},
{
"id": 4,
"type": "CLIPTextEncode",
"pos": [
1848,
790
],
"size": {
"0": 400,
"1": 200
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 43
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
14
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"Royal Samurai holding a samurai sword in battle stance, clothes kimono\n"
]
},
{
"id": 17,
"type": "SAMModelLoader (segment anything)",
"pos": [
1414,
1905
],
"size": {
"0": 315,
"1": 58
},
"flags": {
"collapsed": false
},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "SAM_MODEL",
"type": "SAM_MODEL",
"links": [
21
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "SAMModelLoader (segment anything)"
},
"widgets_values": [
"sam_vit_h (2.56GB)"
]
},
{
"id": 13,
"type": "LoadImage",
"pos": [
975,
1104
],
"size": {
"0": 315,
"1": 314
},
"flags": {},
"order": 6,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
34
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"s-l1200.webp",
"image"
]
},
{
"id": 19,
"type": "Note",
"pos": [
1895,
1993
],
"size": {
"0": 295.87030029296875,
"1": 58
},
"flags": {},
"order": 7,
"mode": 0,
"properties": {
"text": ""
},
"widgets_values": [
"segment anything prompt"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 16,
"type": "GroundingDinoSAMSegment (segment anything)",
"pos": [
1879,
1824
],
"size": {
"0": 352.79998779296875,
"1": 122
},
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "sam_model",
"type": "SAM_MODEL",
"link": 21,
"slot_index": 0
},
{
"name": "grounding_dino_model",
"type": "GROUNDING_DINO_MODEL",
"link": 22,
"slot_index": 1
},
{
"name": "image",
"type": "IMAGE",
"link": 45
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
47
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": [
46
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "GroundingDinoSAMSegment (segment anything)"
},
"widgets_values": [
"shoe",
0.3
]
},
{
"id": 18,
"type": "GroundingDinoModelLoader (segment anything)",
"pos": [
1413,
2045
],
"size": {
"0": 361.20001220703125,
"1": 58
},
"flags": {},
"order": 8,
"mode": 0,
"outputs": [
{
"name": "GROUNDING_DINO_MODEL",
"type": "GROUNDING_DINO_MODEL",
"links": [
22
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "GroundingDinoModelLoader (segment anything)"
},
"widgets_values": [
"GroundingDINO_SwinT_OGC (694MB)"
]
},
{
"id": 15,
"type": "DepthAnythingPreprocessor",
"pos": [
1402,
1731
],
"size": {
"0": 315,
"1": 82
},
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 18
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
19,
48
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "DepthAnythingPreprocessor"
},
"widgets_values": [
"depth_anything_vitl14.pth",
512
]
},
{
"id": 22,
"type": "PreviewImage",
"pos": [
2630,
2148
],
"size": {
"0": 317.80670166015625,
"1": 296.42333984375
},
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 25
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 30,
"type": "PreviewImage",
"pos": [
2242,
2165
],
"size": [
297.55946717544066,
260.8700025236394
],
"flags": {
"collapsed": false
},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 48
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
}
],
"links": [
[
6,
5,
0,
3,
2,
"CONDITIONING"
],
[
8,
6,
0,
3,
3,
"LATENT"
],
[
10,
9,
0,
8,
0,
"MODEL"
],
[
11,
9,
1,
8,
1,
"IPADAPTER"
],
[
14,
4,
0,
11,
0,
"CONDITIONING"
],
[
15,
11,
0,
3,
1,
"CONDITIONING"
],
[
16,
12,
0,
11,
1,
"CONTROL_NET"
],
[
18,
14,
0,
15,
0,
"IMAGE"
],
[
19,
15,
0,
11,
2,
"IMAGE"
],
[
21,
17,
0,
16,
0,
"SAM_MODEL"
],
[
22,
18,
0,
16,
1,
"GROUNDING_DINO_MODEL"
],
[
25,
21,
0,
22,
0,
"IMAGE"
],
[
26,
3,
0,
24,
0,
"LATENT"
],
[
27,
1,
2,
24,
1,
"VAE"
],
[
28,
24,
0,
25,
0,
"IMAGE"
],
[
29,
24,
0,
23,
0,
"IMAGE"
],
[
31,
21,
0,
23,
2,
"IMAGE"
],
[
32,
23,
0,
26,
0,
"IMAGE"
],
[
34,
13,
0,
14,
0,
"IMAGE"
],
[
42,
1,
0,
3,
0,
"MODEL"
],
[
43,
1,
1,
4,
0,
"CLIP"
],
[
44,
1,
1,
5,
0,
"CLIP"
],
[
45,
14,
0,
16,
2,
"IMAGE"
],
[
46,
16,
1,
21,
0,
"MASK"
],
[
47,
16,
0,
23,
1,
"IMAGE"
],
[
48,
15,
0,
30,
0,
"IMAGE"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.5054470284992959,
"offset": {
"0": -961.4580065931495,
"1": -674.5125004824827
}
}
},
"version": 0.4
}