Files
ducido-ObjectFusion_ComfyUI…/workflows/ObjectFusion.json
T

1443 lines
25 KiB
JSON

{
"last_node_id": 102,
"last_link_id": 161,
"nodes": [
{
"id": 79,
"type": "CheckpointLoaderSimple",
"pos": [
2497.118442449664,
498.9760673694416
],
"size": {
"0": 315,
"1": 98
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
108
],
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
148
],
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": [
115
],
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"sd3_medium_incl_clips_t5xxlfp8.safetensors"
]
},
{
"id": 81,
"type": "CLIPTextEncode",
"pos": [
3153.118442449664,
928.9760673694418
],
"size": {
"0": 425.27801513671875,
"1": 180.6060791015625
},
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 147
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
110
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"disfigured, ugly, anime, 3D, painting, scrupture, text, watermark"
]
},
{
"id": 80,
"type": "CLIPTextEncode",
"pos": [
2659.118442449664,
939.9760673694418
],
"size": {
"0": 422.84503173828125,
"1": 164.31304931640625
},
"flags": {},
"order": 21,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 146
},
{
"name": "text",
"type": "STRING",
"link": 160,
"widget": {
"name": "text"
}
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
109
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"The cup is adorned with a charming tableau of a brown and white dog standing on a sidewalk, exuding joy with a smile on its face. The dog is depicted wearing a vibrant purple collar accented with a green tag, adding a pop of color to the scene. Its well-groomed fur and content expression convey a sense of care and happiness. This artistic prompt brings a delightful touch of canine companionship to the cup, portraying a heartwarming moment frozen in time."
]
},
{
"id": 98,
"type": "Reroute",
"pos": [
2937.118442449664,
663.9760673694418
],
"size": [
75,
26
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 148
}
],
"outputs": [
{
"name": "",
"type": "CLIP",
"links": [
146,
147
],
"slot_index": 0
}
],
"properties": {
"showOutputText": false,
"horizontal": false
}
},
{
"id": 82,
"type": "VAEDecode",
"pos": [
3901.118442449664,
538.9760673694417
],
"size": {
"0": 210,
"1": 46
},
"flags": {},
"order": 23,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 114
},
{
"name": "vae",
"type": "VAE",
"link": 115
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
117
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
}
},
{
"id": 68,
"type": "ObjectCrop",
"pos": [
932.7827605711261,
212.9760597400472
],
"size": {
"0": 400,
"1": 200
},
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "Original_image",
"type": "IMAGE",
"link": 139
},
{
"name": "BBOX",
"type": "STRING",
"link": 97,
"widget": {
"name": "BBOX"
}
}
],
"outputs": [
{
"name": "Chosen_Obj",
"type": "IMAGE",
"links": [
122,
150
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "ObjectCrop"
},
"widgets_values": [
0,
""
]
},
{
"id": 56,
"type": "ObjectCrop",
"pos": [
946.3164270830615,
914.7456938304075
],
"size": {
"0": 400,
"1": 200
},
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "Original_image",
"type": "IMAGE",
"link": 142
},
{
"name": "BBOX",
"type": "STRING",
"link": 81,
"widget": {
"name": "BBOX"
}
}
],
"outputs": [
{
"name": "Chosen_Obj",
"type": "IMAGE",
"links": [
83,
151
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "ObjectCrop"
},
"widgets_values": [
0,
""
]
},
{
"id": 100,
"type": "PreviewImage",
"pos": [
954.3164270830617,
1154.7456938304088
],
"size": {
"0": 381.0682067871094,
"1": 258.7750549316406
},
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 151
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 99,
"type": "PreviewImage",
"pos": [
942.7827605711261,
456.9760597400472
],
"size": {
"0": 379.666015625,
"1": 267.19915771484375
},
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 150
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 101,
"type": "Generate Stable Diffsution Prompt With LLM",
"pos": [
1979.9504489225067,
603.1445796954305
],
"size": {
"0": 400,
"1": 446
},
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "object1",
"type": "STRING",
"link": 156,
"widget": {
"name": "object1"
}
},
{
"name": "object2",
"type": "STRING",
"link": 157,
"widget": {
"name": "object2"
}
},
{
"name": "desc_obj1",
"type": "STRING",
"link": 158,
"widget": {
"name": "desc_obj1"
}
},
{
"name": "desc_obj2",
"type": "STRING",
"link": 159,
"widget": {
"name": "desc_obj2"
}
}
],
"outputs": [
{
"name": "stable diffsution prompt",
"type": "STRING",
"links": [
160
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "Generate Stable Diffsution Prompt With LLM"
},
"widgets_values": [
"",
"",
"",
"",
"You are an assistant bot designed to generate creative and detailed descriptions for a Diffusion model to generate realistic image",
"Read these 2 descriptions, really understand them and think about the context where both of them happens together. Then, generate smooth and meaning prompt for diffusion\nThe description for {} is:\n \"{}\"\n The description for {} is:\n \"{}\"",
"",
"",
1,
300,
"mistralai/mistral-7b-instruct:free"
]
},
{
"id": 97,
"type": "Reroute",
"pos": [
322,
980
],
"size": [
75,
26
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 140
}
],
"outputs": [
{
"name": "",
"type": "IMAGE",
"links": [
141,
142
],
"slot_index": 0
}
],
"properties": {
"showOutputText": false,
"horizontal": false
}
},
{
"id": 67,
"type": "ESAM_ModelLoader_Zho",
"pos": [
-115,
807
],
"size": {
"0": 250,
"1": 80
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "esam_model",
"type": "ESAMMODEL",
"links": [
143
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "ESAM_ModelLoader_Zho"
},
"widgets_values": [
"CUDA"
]
},
{
"id": 95,
"type": "Reroute",
"pos": [
167,
808
],
"size": [
75,
26
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 143
}
],
"outputs": [
{
"name": "",
"type": "ESAMMODEL",
"links": [
135,
136
],
"slot_index": 0
}
],
"properties": {
"showOutputText": false,
"horizontal": false
}
},
{
"id": 94,
"type": "Reroute",
"pos": [
186,
688
],
"size": [
75,
26
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 161
}
],
"outputs": [
{
"name": "",
"type": "YOLOWORLDMODEL",
"links": [
132,
133
],
"slot_index": 0
}
],
"properties": {
"showOutputText": false,
"horizontal": false
}
},
{
"id": 96,
"type": "Reroute",
"pos": [
310,
134
],
"size": [
75,
26
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 144
}
],
"outputs": [
{
"name": "",
"type": "IMAGE",
"links": [
138,
139
],
"slot_index": 0
}
],
"properties": {
"showOutputText": false,
"horizontal": false
}
},
{
"id": 64,
"type": "LoadImage",
"pos": [
-287,
69
],
"size": [
575.8929198243384,
583.698507518247
],
"flags": {},
"order": 2,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
144
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"manycups.jpg",
"image"
]
},
{
"id": 51,
"type": "LoadImage",
"pos": [
-294,
975
],
"size": {
"0": 591.8458251953125,
"1": 703.8153686523438
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
140
],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"bus.jpeg",
"image"
]
},
{
"id": 65,
"type": "Yoloworld_ModelLoader_Zho",
"pos": [
-123,
687
],
"size": {
"0": 250,
"1": 80
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "yolo_world_model",
"type": "YOLOWORLDMODEL",
"links": [
161
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "Yoloworld_ModelLoader_Zho"
},
"widgets_values": [
"yolo_world/l"
]
},
{
"id": 84,
"type": "PreviewImage",
"pos": [
3672,
635
],
"size": [
474.6462684690068,
402.3494239092297
],
"flags": {},
"order": 24,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 117
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 85,
"type": "EmptyLatentImage",
"pos": [
2500.118442449664,
340.9760673694416
],
"size": {
"0": 315,
"1": 106
},
"flags": {},
"order": 5,
"mode": 0,
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
130
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
1024,
1024,
1
]
},
{
"id": 52,
"type": "Yoloworld_ESAM_Zho",
"pos": [
510.2162860343707,
920.2652267603027
],
"size": {
"0": 416.34600830078125,
"1": 419.03369140625
},
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "yolo_world_model",
"type": "YOLOWORLDMODEL",
"link": 133
},
{
"name": "esam_model",
"type": "ESAMMODEL",
"link": 136,
"slot_index": 1
},
{
"name": "image",
"type": "IMAGE",
"link": 141,
"slot_index": 2
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": [],
"shape": 3,
"slot_index": 1
},
{
"name": "BBOX",
"type": "STRING",
"links": [
81
],
"shape": 3,
"slot_index": 2
},
{
"name": "CATEGORIES",
"type": "STRING",
"links": [
157
],
"shape": 3,
"slot_index": 3
}
],
"properties": {
"Node name for S&R": "Yoloworld_ESAM_Zho"
},
"widgets_values": [
"bus",
0.01,
0.6,
2,
2,
1,
true,
false,
false,
false,
false,
0
]
},
{
"id": 78,
"type": "KSampler",
"pos": [
3530,
239
],
"size": {
"0": 335.6715087890625,
"1": 275.1487121582031
},
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 108
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 109
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 110
},
{
"name": "latent_image",
"type": "LATENT",
"link": 130,
"slot_index": 3
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
114
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
648274518118444,
"randomize",
35,
8,
"dpmpp_2m",
"normal",
1
]
},
{
"id": 74,
"type": "Yoloworld_ESAM_Zho",
"pos": [
526.7827605711261,
208.9760597400472
],
"size": {
"0": 400,
"1": 400
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "yolo_world_model",
"type": "YOLOWORLDMODEL",
"link": 132
},
{
"name": "esam_model",
"type": "ESAMMODEL",
"link": 135
},
{
"name": "image",
"type": "IMAGE",
"link": 138
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [],
"shape": 3,
"slot_index": 0
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 3
},
{
"name": "BBOX",
"type": "STRING",
"links": [
97
],
"shape": 3,
"slot_index": 2
},
{
"name": "CATEGORIES",
"type": "STRING",
"links": [
156
],
"shape": 3,
"slot_index": 3
}
],
"properties": {
"Node name for S&R": "Yoloworld_ESAM_Zho"
},
"widgets_values": [
"cup in the middle",
0.01,
0.6,
2,
2,
1,
true,
false,
false,
false,
false,
0
]
},
{
"id": 88,
"type": "img2txt BLIP/Llava Multimodel Tagger",
"pos": [
1354.7827605711268,
222.9760597400472
],
"size": {
"0": 430,
"1": 490
},
"flags": {},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "input_image",
"type": "IMAGE",
"link": 122
}
],
"outputs": [
{
"name": "caption",
"type": "STRING",
"links": [
158
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "img2txt BLIP/Llava Multimodel Tagger"
},
"widgets_values": [
false,
true,
false,
false,
"",
"Describe in detail the object shown in the image, focusing exclusively on its physical attributes, colors, and any visible accessories",
0.8300000000000001,
1.2,
36,
274,
5,
"",
"The image features a blue cup sitting on a table. The cup is made of ceramic material and has a smooth, curved surface. The cup is placed on a white plate, which is also visible in the scene. The blue color of the cup contrasts with the white plate, creating a visually appealing presentation, </s>, "
]
},
{
"id": 58,
"type": "img2txt BLIP/Llava Multimodel Tagger",
"pos": [
1361.3164270830612,
918.7456938304077
],
"size": {
"0": 430,
"1": 490
},
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "input_image",
"type": "IMAGE",
"link": 83
}
],
"outputs": [
{
"name": "caption",
"type": "STRING",
"links": [
159
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "img2txt BLIP/Llava Multimodel Tagger"
},
"widgets_values": [
false,
true,
false,
false,
"",
"Describe in detail the object shown in the image, focusing exclusively on its physical attributes, colors, and any visible accessories",
0.75,
1.2,
99,
256,
5,
"",
"The image features a large white bus with blue stripes on its side. The bus is parked on the side of the road, and it appears to be a tour bus. The bus has multiple rows of seats, providing ample space for passengers. The blue stripes on the bus add a touch of color to the otherwise white vehicle, </s>, "
]
}
],
"links": [
[
81,
52,
2,
56,
1,
"STRING"
],
[
83,
56,
0,
58,
0,
"IMAGE"
],
[
97,
74,
2,
68,
1,
"STRING"
],
[
108,
79,
0,
78,
0,
"MODEL"
],
[
109,
80,
0,
78,
1,
"CONDITIONING"
],
[
110,
81,
0,
78,
2,
"CONDITIONING"
],
[
114,
78,
0,
82,
0,
"LATENT"
],
[
115,
79,
2,
82,
1,
"VAE"
],
[
117,
82,
0,
84,
0,
"IMAGE"
],
[
122,
68,
0,
88,
0,
"IMAGE"
],
[
130,
85,
0,
78,
3,
"LATENT"
],
[
132,
94,
0,
74,
0,
"YOLOWORLDMODEL"
],
[
133,
94,
0,
52,
0,
"YOLOWORLDMODEL"
],
[
135,
95,
0,
74,
1,
"ESAMMODEL"
],
[
136,
95,
0,
52,
1,
"ESAMMODEL"
],
[
138,
96,
0,
74,
2,
"IMAGE"
],
[
139,
96,
0,
68,
0,
"IMAGE"
],
[
140,
51,
0,
97,
0,
"*"
],
[
141,
97,
0,
52,
2,
"IMAGE"
],
[
142,
97,
0,
56,
0,
"IMAGE"
],
[
143,
67,
0,
95,
0,
"*"
],
[
144,
64,
0,
96,
0,
"*"
],
[
146,
98,
0,
80,
0,
"CLIP"
],
[
147,
98,
0,
81,
0,
"CLIP"
],
[
148,
79,
1,
98,
0,
"*"
],
[
150,
68,
0,
99,
0,
"IMAGE"
],
[
151,
56,
0,
100,
0,
"IMAGE"
],
[
156,
74,
3,
101,
0,
"STRING"
],
[
157,
52,
3,
101,
1,
"STRING"
],
[
158,
88,
0,
101,
2,
"STRING"
],
[
159,
58,
0,
101,
3,
"STRING"
],
[
160,
101,
0,
80,
1,
"STRING"
],
[
161,
65,
0,
94,
0,
"*"
]
],
"groups": [
{
"title": "Diffusion",
"bounding": [
2489,
182,
1708,
926
],
"color": "#b06634",
"font_size": 70,
"locked": false
},
{
"title": "Get description for object 1",
"bounding": [
448,
77,
1409,
692
],
"color": "#a1309b",
"font_size": 70,
"locked": false
},
{
"title": "Get description for object 2",
"bounding": [
439,
777,
1413,
688
],
"color": "#a1309b",
"font_size": 70,
"locked": false
},
{
"title": "Generate prompt",
"bounding": [
1875,
438,
585,
639
],
"color": "#b58b2a",
"font_size": 70,
"locked": false
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.2853116706110091,
"offset": {
"0": 558.0238902393447,
"1": 400.39068906211764
}
}
},
"version": 0.4
}