Files
SeanScripts-ComfyUI-Pixtral…/examples/dataset_captioning_workflow.json
T

522 lines
9.1 KiB
JSON

{
"last_node_id": 25,
"last_link_id": 24,
"nodes": [
{
"id": 17,
"type": "Note",
"pos": {
"0": 1864,
"1": 871
},
"size": {
"0": 260.5903625488281,
"1": 137.3493194580078
},
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Folder within the ComfyUI output folder where you want the images + captions to be saved with the same name (1.png, 1.txt, etc.)"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 16,
"type": "Note",
"pos": {
"0": 1864,
"1": 431
},
"size": {
"0": 282.4085388183594,
"1": 132.3493194580078
},
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Path here should be the same as the path below, but as a relative path from where you are running ComfyUI, or as an absolute path"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 18,
"type": "Note",
"pos": {
"0": 267,
"1": 795
},
"size": {
"0": 279.317626953125,
"1": 145.62205505371094
},
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Path to a folder with the images you want to caption (filenames don't matter).\nimage_load_cap = 0 will load all the images from the folder."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 24,
"type": "MolmoGenerateText",
"pos": {
"0": 990,
"1": 401
},
"size": {
"0": 400,
"1": 362
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "molmo_model",
"type": "VISION_MODEL",
"link": 22
},
{
"name": "images",
"type": "IMAGE",
"link": 23
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": [
24
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MolmoGenerateText"
},
"widgets_values": [
"",
"Describe this image in detail. ",
256,
true,
0.3,
0.9,
40,
"<|endoftext|>",
3561946545,
"randomize",
false
]
},
{
"id": 23,
"type": "MolmoModelLoader",
"pos": {
"0": 572,
"1": 407
},
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VISION_MODEL",
"type": "VISION_MODEL",
"links": [
22
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MolmoModelLoader"
},
"widgets_values": [
"molmo-7B-D-bnb-4bit"
]
},
{
"id": 19,
"type": "Note",
"pos": {
"0": 290,
"1": 368
},
"size": {
"0": 264.54547119140625,
"1": 134.54547119140625
},
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Llama 3.2 11B Vision and Molmo are probably better quality than Pixtral for this"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 8,
"type": "Save Text File",
"pos": {
"0": 1537,
"1": 407
},
"size": {
"0": 303.0448913574219,
"1": 174
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "text",
"type": "STRING",
"link": 24,
"widget": {
"name": "text"
}
},
{
"name": "filename_prefix",
"type": "STRING",
"link": 9,
"widget": {
"name": "filename_prefix"
}
}
],
"outputs": [],
"properties": {
"Node name for S&R": "Save Text File"
},
"widgets_values": [
"",
".\\ComfyUI\\output\\images_with_captions",
"",
"",
0,
".txt",
"utf-8"
]
},
{
"id": 4,
"type": "ListCounter //Inspire",
"pos": {
"0": 954,
"1": 864
},
"size": {
"0": 210,
"1": 58
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "signal",
"type": "*",
"link": 3
}
],
"outputs": [
{
"name": "INT",
"type": "INT",
"links": [
1
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "ListCounter //Inspire"
},
"widgets_values": [
1
]
},
{
"id": 6,
"type": "SomethingToString",
"pos": {
"0": 1223,
"1": 865
},
"size": {
"0": 210,
"1": 82
},
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "input",
"type": "*",
"link": 1
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": [
9,
14,
15
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "SomethingToString"
},
"widgets_values": [
"",
""
]
},
{
"id": 1,
"type": "LoadImageListFromDir //Inspire",
"pos": {
"0": 570,
"1": 786
},
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
3,
13,
23
],
"slot_index": 0,
"shape": 6
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 6
},
{
"name": "FILE PATH",
"type": "STRING",
"links": null,
"shape": 6
}
],
"properties": {
"Node name for S&R": "LoadImageListFromDir //Inspire"
},
"widgets_values": [
"E:\\datasets\\example",
0,
0,
false
]
},
{
"id": 13,
"type": "> Save Image",
"pos": {
"0": 1540,
"1": 790
},
"size": {
"0": 299.77215576171875,
"1": 406
},
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 13
},
{
"name": "filename_opt",
"type": "STRING",
"link": 14,
"widget": {
"name": "filename_opt"
}
},
{
"name": "filename_prefix",
"type": "STRING",
"link": 15,
"widget": {
"name": "filename_prefix"
}
}
],
"outputs": [],
"properties": {
"Node name for S&R": "> Save Image"
},
"widgets_values": [
"",
"images_with_captions",
false,
false,
"png",
100,
""
]
},
{
"id": 25,
"type": "Note",
"pos": {
"0": 1301,
"1": 1068
},
"size": [
221.29719695532322,
122.35482607937593
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"This node is from ComfyUI_yanc, idk why \"Install Missing Custom Nodes\" doesn't work for this one"
],
"color": "#432",
"bgcolor": "#653"
}
],
"links": [
[
1,
4,
0,
6,
0,
"*"
],
[
3,
1,
0,
4,
0,
"*"
],
[
9,
6,
0,
8,
1,
"STRING"
],
[
13,
1,
0,
13,
0,
"IMAGE"
],
[
14,
6,
0,
13,
1,
"STRING"
],
[
15,
6,
0,
13,
2,
"STRING"
],
[
22,
23,
0,
24,
0,
"VISION_MODEL"
],
[
23,
1,
0,
24,
1,
"IMAGE"
],
[
24,
24,
0,
8,
0,
"STRING"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.7513148009015777,
"offset": [
-54.49319695532304,
20.897173920624354
]
}
},
"version": 0.4
}