Error: Invalid JSON format
```json
{
"last_node_id": 12,
"last_link_id": 18,
"nodes": [
{
"id": 1,
"type": "CheckpointLoader",
"pos": [
100,
100
],
"size": [
315,
106
],
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5
]
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
6,
7
]
},
{
"name": "VAE",
"type": "VAE",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "CheckpointLoader"
},
"widgets_values": [
"v1-5-pruned-emaonly.ckpt"
]
},
{
"id": 2,
"type": "CLIPTextEncode",
"pos": [
500,
100
],
"size": [
425,
180
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 6
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
9
]
}
],
"title": "Positive Prompt",
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"beautiful scenery nature glass bottle landscape, purple galaxy bottle, 1girl, standing,long hair, open mouth, best quality, highly detailed, dramatic lighting"
]
},
{
"id": 3,
"type": "CLIPTextEncode",
"pos": [
500,
320
],
"size": [
425,
180
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 7
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
10
]
}
],
"title": "Negative Prompt",
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"lowres, bad anatomy, bad hands, text, error, missing fingers, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"
]
},
{
"id": 4,
"type": "EmptyLatentImage",
"pos": [
100,
300
],
"size": [
315,
106
],
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
11
]
}
],
"title": "Empty Latent Image",
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
512,
512,
1
]
},
{
"id": 5,
"type": "KSampler",
"pos": [
500,
550
],
"size": [
315,
262
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"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
]
}
],
"title": "KSampler",
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
42,
"randomize",
20,
7.0,
"dpmpp_2m",
"karras"
]
},
{
"id": 6,
"type": "VAEDecode",
"pos": [
900,
550
],
"size": [
210,
46
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 12
},
{
"name": "vae",
"type": "VAE",
"link": 8
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
17
]
}
],
"title": "VAE Decode",
"properties": {
"Node name for S&R": "VAEDecode"
}
},
{
"id": 7,
"type": "SaveImage",
"pos": [
1150,
550
],
"size": [
315,
270
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 17
}
],
"title": "Save Image",
"properties": {
"Node name for S&R": "SaveImage"
},
"widgets_values": [
"ComfyUI_Stable_Diffusion"
]
},
{
"id": 8,
"type": "CLIPVisionLoader",
"pos": [
100,
450
],
"size": [
315,
58
],
"flags": {},
"order": 7,
"mode": 0,
"outputs": [
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": [
13
]
}
],
"title": "CLIP Vision Loader",
"properties": {
"Node name for S&R": "CLIPVisionLoader"
},
"widgets_values": [
"model.safetensors"
]
},
{
"id": 9,
"type": "ImageOnlyCheckpointLoader",
"pos": [
100,
550
],
"size": [
315,
58
],
"flags": {},
"order": 8,
"mode": 0,
"outputs": [
{
"name": "IMAGE_ENCODER",
"type": "IMAGE_ENCODER",
"links": [
14
]
}
],
"title": "Image Only Checkpoint Loader",
"properties": {
"Node name for S&R": "ImageOnlyCheckpointLoader"
},
"widgets_values": [
"model.safetensors"
]
},
{
"id": 10,
"type": "CLIPTextEncode",
"pos": [
500,
700
],
"size": [
425,
100
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 15
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
16
]
}
],
"title": "Prompt",
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"a photo of a cat"
]
},
{
"id": 11,
"type": "CLIPVisionLoader",
"pos": [
100,
650
],
"size": [
315,
58
],
"flags": {},
"order": 10,
"mode": 0,
"outputs": [
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": [
18
]
}
],
"title": "CLIP Vision Loader",
"properties": {
"Node name for S&R": "CLIPVisionLoader"
},
"widgets_values": [
"model.safetensors"
]
},
{
"id": 12,
"type": "CLIPTextEncode",
"pos": [
950,
300
],
"size": [
300,
200
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 16
}
],
"outputs": [],
"title": "CLIPTextEncode",
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"a photo of a cat"
]
}
],
"links": [
[
5,
1,
0,
5,
0,
"MODEL"
],
[
6,
1,
1,
2,
0,
"CLIP"
],
[
7,
1,
1,
3,
0,
"CLIP"
],
[
8,
1,
2,
6,
1,
"VAE"
],
[
9,
2,
0,
5,
1,
"CONDITIONING"
],
[
10,
3,
0,
5,
2,
"CONDITIONING"
],
[
11,
4,
0,
5,
3,
"LATENT"
],
[
12,
5,
0,
6,
0,
"LATENT"
],
[
13,
8,
0,
10,
0,
"CLIP_VISION"
],
[
14,
9,
0,
10,
1,
"IMAGE_ENCODER"
],
[
15,
1,
1,
10,
2,
"CLIP"
],
[
16,
10,
0,
12,
0,
"CONDITIONING"
],
[
17,
6,
0,
7,
0,
"IMAGE"
],
[
18,
11,
0,
12,
1,
"CLIP_VISION"
]
],
"groups": [
{
"title": "Stable Diffusion Core",
"bounding": [
50,
50,
900,
550
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "CLIP Vision",
"bounding": [
50,
450,
400,
300
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Image Processing",
"bounding": [
450,
650,
900,
350
],
"color": "#3f789e",
"font_size": 24
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.5,
"offset": [
-100,
-100
]
}
}
}
```
This ComfyUI workflow provides a complete stable diffusion setup with:
**Core Features:**
- **Model Loading**: Loads stable diffusion checkpoints with model, CLIP, and VAE
- **Text Encoding**: Positive and negative prompt encoding for guided generation
- **Sampling**: KSampler with configurable steps, CFG scale, and sampler type
- **Image Output**: VAE decoding and image saving
**Key Parameters:**
- Default model: `v1-5-pruned-emaonly.ckpt`
- Resolution: 512x512
- Sampling steps: 20
- CFG scale: 7.0
- Sampler: `dpmpp_2m` with `karras` scheduling
**Usage:**
1. Load the workflow in ComfyUI
2. Install required models in the models folder
3. Adjust prompts and parameters as needed
4. Queue the generation
The workflow includes additional CLIP Vision nodes for advanced features like image-to-image generation if needed. Built with anycoder - https: //huggingface.co/spaces/akhaliq/anycoder