Vision-language model nodes for ComfyUI using Tencent's Penguin-VL. Includes image query, video query, batch image query, and model loader nodes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
236 lines
4.1 KiB
JSON
236 lines
4.1 KiB
JSON
{
|
|
"id": "4fba64e6-833a-41a4-8f3c-02f030da13b5",
|
|
"revision": 0,
|
|
"last_node_id": 11,
|
|
"last_link_id": 22,
|
|
"nodes": [
|
|
{
|
|
"id": 11,
|
|
"type": "FL_PenguinVL_BatchImageQuery",
|
|
"pos": [
|
|
2580.0190145258357,
|
|
5068.568665419667
|
|
],
|
|
"size": [
|
|
400,
|
|
306
|
|
],
|
|
"flags": {},
|
|
"order": 3,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "FL_PENGUINVL_MODEL",
|
|
"link": 21
|
|
},
|
|
{
|
|
"name": "images",
|
|
"type": "IMAGE",
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "text",
|
|
"type": "STRING",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_PenguinVL_BatchImageQuery"
|
|
},
|
|
"widgets_values": [
|
|
"Describe this image.",
|
|
"",
|
|
256,
|
|
0.7,
|
|
0.9,
|
|
true,
|
|
"\n---\n",
|
|
1024
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "FL_PenguinVL_ImageQuery",
|
|
"pos": [
|
|
3009.8725795200726,
|
|
5073.9158207704795
|
|
],
|
|
"size": [
|
|
400,
|
|
282
|
|
],
|
|
"flags": {},
|
|
"order": 1,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "FL_PENGUINVL_MODEL",
|
|
"link": 5
|
|
},
|
|
{
|
|
"name": "image",
|
|
"type": "IMAGE",
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "text",
|
|
"type": "STRING",
|
|
"links": []
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_PenguinVL_ImageQuery"
|
|
},
|
|
"widgets_values": [
|
|
"what color is the characters shirt",
|
|
"",
|
|
512,
|
|
0.7,
|
|
0.9,
|
|
true,
|
|
1024
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "FL_PenguinVL_LoadModel",
|
|
"pos": [
|
|
2297.983154297023,
|
|
4835.0458948174455
|
|
],
|
|
"size": [
|
|
272.63046875,
|
|
154
|
|
],
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "FL_PENGUINVL_MODEL",
|
|
"links": [
|
|
5,
|
|
7,
|
|
21
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_PenguinVL_LoadModel"
|
|
},
|
|
"widgets_values": [
|
|
"2B",
|
|
"auto",
|
|
"auto",
|
|
true,
|
|
false
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
},
|
|
{
|
|
"id": 7,
|
|
"type": "FL_PenguinVL_VideoQuery",
|
|
"pos": [
|
|
3437.040604224414,
|
|
5074.071486119074
|
|
],
|
|
"size": [
|
|
400,
|
|
306
|
|
],
|
|
"flags": {},
|
|
"order": 2,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "FL_PENGUINVL_MODEL",
|
|
"link": 7
|
|
},
|
|
{
|
|
"name": "images",
|
|
"type": "IMAGE",
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "text",
|
|
"type": "STRING",
|
|
"links": []
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "FL_PenguinVL_VideoQuery"
|
|
},
|
|
"widgets_values": [
|
|
"whats happening in this video",
|
|
"",
|
|
64,
|
|
512,
|
|
0.7,
|
|
0.9,
|
|
true,
|
|
1024
|
|
],
|
|
"color": "#16727c",
|
|
"bgcolor": "#4F0074"
|
|
}
|
|
],
|
|
"links": [
|
|
[
|
|
5,
|
|
6,
|
|
0,
|
|
2,
|
|
0,
|
|
"FL_PENGUINVL_MODEL"
|
|
],
|
|
[
|
|
7,
|
|
6,
|
|
0,
|
|
7,
|
|
0,
|
|
"FL_PENGUINVL_MODEL"
|
|
],
|
|
[
|
|
21,
|
|
6,
|
|
0,
|
|
11,
|
|
0,
|
|
"FL_PENGUINVL_MODEL"
|
|
]
|
|
],
|
|
"groups": [],
|
|
"config": {},
|
|
"extra": {
|
|
"ds": {
|
|
"scale": 1.2380375700855237,
|
|
"offset": [
|
|
-2123.1023599302207,
|
|
-4606.599107157883
|
|
]
|
|
},
|
|
"frontendVersion": "1.39.19",
|
|
"VHS_latentpreview": false,
|
|
"VHS_latentpreviewrate": 0,
|
|
"VHS_MetadataImage": true,
|
|
"VHS_KeepIntermediate": true
|
|
},
|
|
"version": 0.4
|
|
} |