Sebastian Krüger
904a70df76
Change CLIP vision model from ViT-H to ViT-bigG to match the VIT-G preset in IPAdapterUnifiedLoader. This fixes dimension mismatch error (1280 vs 768). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
675 lines
11 KiB
JSON
675 lines
11 KiB
JSON
{
|
|
"last_node_id": 16,
|
|
"last_link_id": 21,
|
|
"nodes": [
|
|
{
|
|
"id": 1,
|
|
"type": "CheckpointLoaderSimple",
|
|
"pos": [
|
|
50,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 350,
|
|
"1": 100
|
|
},
|
|
"widgets_values": [
|
|
"sd_xl_base_1.0.safetensors"
|
|
],
|
|
"title": "SDXL Base Checkpoint Loader",
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "CheckpointLoaderSimple"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "MODEL",
|
|
"type": "MODEL",
|
|
"links": [
|
|
1
|
|
],
|
|
"slot_index": 0
|
|
},
|
|
{
|
|
"name": "CLIP",
|
|
"type": "CLIP",
|
|
"links": [
|
|
6,
|
|
7
|
|
],
|
|
"slot_index": 1
|
|
},
|
|
{
|
|
"name": "VAE",
|
|
"type": "VAE",
|
|
"links": [
|
|
13
|
|
],
|
|
"slot_index": 2
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "LoadImage",
|
|
"pos": [
|
|
50,
|
|
300
|
|
],
|
|
"size": [
|
|
315,
|
|
314
|
|
],
|
|
"widgets_values": [
|
|
"face_reference.png",
|
|
"image"
|
|
],
|
|
"title": "API Face Reference Input",
|
|
"flags": {},
|
|
"order": 1,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "LoadImage"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "IMAGE",
|
|
"type": "IMAGE",
|
|
"links": [
|
|
3
|
|
],
|
|
"slot_index": 0
|
|
},
|
|
{
|
|
"name": "MASK",
|
|
"type": "MASK",
|
|
"links": [],
|
|
"slot_index": 1
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "IPAdapterUnifiedLoader",
|
|
"pos": [
|
|
450,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 315,
|
|
"1": 78
|
|
},
|
|
"widgets_values": [
|
|
"VIT-G (medium strength)"
|
|
],
|
|
"title": "IP-Adapter Face Loader",
|
|
"flags": {},
|
|
"order": 2,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "IPAdapterUnifiedLoader"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "MODEL",
|
|
"link": 1
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "MODEL",
|
|
"type": "MODEL",
|
|
"links": [
|
|
4
|
|
],
|
|
"slot_index": 0
|
|
},
|
|
{
|
|
"name": "IPADAPTER",
|
|
"type": "IPADAPTER",
|
|
"links": [
|
|
5
|
|
],
|
|
"slot_index": 1
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "IPAdapterAdvanced",
|
|
"pos": [
|
|
800,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 315,
|
|
"1": 258
|
|
},
|
|
"widgets_values": [
|
|
0.85,
|
|
"ease in-out",
|
|
"average",
|
|
0.0,
|
|
1.0,
|
|
"V only"
|
|
],
|
|
"title": "Apply IP-Adapter Face",
|
|
"flags": {},
|
|
"order": 3,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "IPAdapterAdvanced"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "MODEL",
|
|
"link": 4
|
|
},
|
|
{
|
|
"name": "ipadapter",
|
|
"type": "IPADAPTER",
|
|
"link": 5
|
|
},
|
|
{
|
|
"name": "image",
|
|
"type": "IMAGE",
|
|
"link": 3
|
|
},
|
|
{
|
|
"name": "clip_vision",
|
|
"type": "CLIP_VISION",
|
|
"link": 20
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "MODEL",
|
|
"type": "MODEL",
|
|
"links": [
|
|
8
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 5,
|
|
"type": "CLIPTextEncode",
|
|
"pos": [
|
|
450,
|
|
400
|
|
],
|
|
"size": {
|
|
"0": 400,
|
|
"1": 200
|
|
},
|
|
"widgets_values": [
|
|
"A professional portrait, studio lighting, detailed face"
|
|
],
|
|
"title": "API Positive Prompt",
|
|
"flags": {},
|
|
"order": 4,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "CLIPTextEncode"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "clip",
|
|
"type": "CLIP",
|
|
"link": 6
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "CONDITIONING",
|
|
"type": "CONDITIONING",
|
|
"links": [
|
|
9
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "CLIPTextEncode",
|
|
"pos": [
|
|
450,
|
|
650
|
|
],
|
|
"size": {
|
|
"0": 400,
|
|
"1": 200
|
|
},
|
|
"widgets_values": [
|
|
"blurry, distorted face, low quality"
|
|
],
|
|
"title": "API Negative Prompt",
|
|
"flags": {},
|
|
"order": 5,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "CLIPTextEncode"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "clip",
|
|
"type": "CLIP",
|
|
"link": 7
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "CONDITIONING",
|
|
"type": "CONDITIONING",
|
|
"links": [
|
|
10
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 7,
|
|
"type": "EmptyLatentImage",
|
|
"pos": [
|
|
800,
|
|
450
|
|
],
|
|
"size": {
|
|
"0": 315,
|
|
"1": 106
|
|
},
|
|
"widgets_values": [
|
|
1024,
|
|
1024,
|
|
1
|
|
],
|
|
"title": "API Latent Image Config",
|
|
"flags": {},
|
|
"order": 6,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "EmptyLatentImage"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "LATENT",
|
|
"type": "LATENT",
|
|
"links": [
|
|
11
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 8,
|
|
"type": "KSampler",
|
|
"pos": [
|
|
1170,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 315,
|
|
"1": 474
|
|
},
|
|
"widgets_values": [
|
|
42,
|
|
"fixed",
|
|
30,
|
|
6.5,
|
|
"dpmpp_2m",
|
|
"karras",
|
|
1
|
|
],
|
|
"title": "Sampler with Face",
|
|
"flags": {},
|
|
"order": 7,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "KSampler"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "model",
|
|
"type": "MODEL",
|
|
"link": 8
|
|
},
|
|
{
|
|
"name": "positive",
|
|
"type": "CONDITIONING",
|
|
"link": 9
|
|
},
|
|
{
|
|
"name": "negative",
|
|
"type": "CONDITIONING",
|
|
"link": 10
|
|
},
|
|
{
|
|
"name": "latent_image",
|
|
"type": "LATENT",
|
|
"link": 11
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "LATENT",
|
|
"type": "LATENT",
|
|
"links": [
|
|
12
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 9,
|
|
"type": "VAEDecode",
|
|
"pos": [
|
|
1540,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 210,
|
|
"1": 46
|
|
},
|
|
"title": "VAE Decode",
|
|
"flags": {},
|
|
"order": 8,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "VAEDecode"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "samples",
|
|
"type": "LATENT",
|
|
"link": 12
|
|
},
|
|
{
|
|
"name": "vae",
|
|
"type": "VAE",
|
|
"link": 13
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"name": "IMAGE",
|
|
"type": "IMAGE",
|
|
"links": [
|
|
14,
|
|
15
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "PreviewImage",
|
|
"pos": [
|
|
1800,
|
|
100
|
|
],
|
|
"size": {
|
|
"0": 400,
|
|
"1": 400
|
|
},
|
|
"title": "Preview Output",
|
|
"flags": {},
|
|
"order": 9,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "PreviewImage"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "images",
|
|
"type": "IMAGE",
|
|
"link": 14
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 11,
|
|
"type": "SaveImage",
|
|
"pos": [
|
|
1800,
|
|
550
|
|
],
|
|
"size": {
|
|
"0": 400,
|
|
"1": 100
|
|
},
|
|
"widgets_values": [
|
|
"ipadapter_face_output"
|
|
],
|
|
"title": "API Image Output",
|
|
"flags": {},
|
|
"order": 10,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "SaveImage"
|
|
},
|
|
"inputs": [
|
|
{
|
|
"name": "images",
|
|
"type": "IMAGE",
|
|
"link": 15
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 12,
|
|
"type": "CLIPVisionLoader",
|
|
"pos": [
|
|
450,
|
|
250
|
|
],
|
|
"size": {
|
|
"0": 315,
|
|
"1": 58
|
|
},
|
|
"widgets_values": [
|
|
"CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors"
|
|
],
|
|
"title": "CLIP Vision Loader",
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"properties": {
|
|
"Node name for S&R": "CLIPVisionLoader"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "CLIP_VISION",
|
|
"type": "CLIP_VISION",
|
|
"links": [
|
|
20
|
|
],
|
|
"slot_index": 0
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"links": [
|
|
[
|
|
1,
|
|
1,
|
|
0,
|
|
3,
|
|
0,
|
|
"MODEL"
|
|
],
|
|
[
|
|
3,
|
|
2,
|
|
0,
|
|
4,
|
|
2,
|
|
"IMAGE"
|
|
],
|
|
[
|
|
4,
|
|
3,
|
|
0,
|
|
4,
|
|
0,
|
|
"MODEL"
|
|
],
|
|
[
|
|
5,
|
|
3,
|
|
1,
|
|
4,
|
|
1,
|
|
"IPADAPTER"
|
|
],
|
|
[
|
|
6,
|
|
1,
|
|
1,
|
|
5,
|
|
0,
|
|
"CLIP"
|
|
],
|
|
[
|
|
7,
|
|
1,
|
|
1,
|
|
6,
|
|
0,
|
|
"CLIP"
|
|
],
|
|
[
|
|
8,
|
|
4,
|
|
0,
|
|
8,
|
|
0,
|
|
"MODEL"
|
|
],
|
|
[
|
|
9,
|
|
5,
|
|
0,
|
|
8,
|
|
1,
|
|
"CONDITIONING"
|
|
],
|
|
[
|
|
10,
|
|
6,
|
|
0,
|
|
8,
|
|
2,
|
|
"CONDITIONING"
|
|
],
|
|
[
|
|
11,
|
|
7,
|
|
0,
|
|
8,
|
|
3,
|
|
"LATENT"
|
|
],
|
|
[
|
|
12,
|
|
8,
|
|
0,
|
|
9,
|
|
0,
|
|
"LATENT"
|
|
],
|
|
[
|
|
13,
|
|
1,
|
|
2,
|
|
9,
|
|
1,
|
|
"VAE"
|
|
],
|
|
[
|
|
14,
|
|
9,
|
|
0,
|
|
10,
|
|
0,
|
|
"IMAGE"
|
|
],
|
|
[
|
|
15,
|
|
9,
|
|
0,
|
|
11,
|
|
0,
|
|
"IMAGE"
|
|
],
|
|
[
|
|
20,
|
|
12,
|
|
0,
|
|
4,
|
|
3,
|
|
"CLIP_VISION"
|
|
]
|
|
],
|
|
"extra": {
|
|
"workflow_info": {
|
|
"name": "IP-Adapter Face Portrait Image-to-Image Production",
|
|
"version": "1.0.0",
|
|
"description": "Face-focused generation using IP-Adapter Face model. Transfer facial features from reference to generate new portraits or perform face swaps.",
|
|
"category": "image-to-image",
|
|
"tags": [
|
|
"ipadapter",
|
|
"face",
|
|
"portrait",
|
|
"i2i",
|
|
"production"
|
|
],
|
|
"requirements": {
|
|
"models": [
|
|
"stable-diffusion-xl-base-1.0",
|
|
"ip-adapter-face"
|
|
],
|
|
"custom_nodes": [
|
|
"ComfyUI_IPAdapter_plus"
|
|
],
|
|
"vram_min": "16GB"
|
|
},
|
|
"parameters": {
|
|
"face_image": {
|
|
"node_id": 2,
|
|
"type": "image",
|
|
"required": true,
|
|
"description": "Reference face image"
|
|
},
|
|
"prompt": {
|
|
"node_id": 5,
|
|
"type": "string",
|
|
"default": "A professional portrait",
|
|
"description": "Portrait description"
|
|
},
|
|
"face_weight": {
|
|
"node_id": 4,
|
|
"type": "float",
|
|
"default": 0.85,
|
|
"description": "Face similarity strength (0.85 recommended)"
|
|
}
|
|
},
|
|
"use_cases": [
|
|
"Portrait generation with specific face",
|
|
"Face swap in different contexts",
|
|
"Consistent character portraits",
|
|
"Professional headshots"
|
|
]
|
|
}
|
|
},
|
|
"version": 0.4
|
|
} |