Files
runpod/comfyui/workflows/text-to-image/sd35-large-t2i-production-v1.json
Sebastian Krüger 5c1e9d092b fix: rebuild SD3.5 workflow with TripleCLIPLoader
SD3.5 checkpoint doesn't contain CLIP encoders. Now using:
- CheckpointLoaderSimple for MODEL and VAE
- TripleCLIPLoader for CLIP-L, CLIP-G, and T5-XXL
- Standard CLIPTextEncode for prompts

This fixes the "clip input is invalid: None" error.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 10:56:09 +01:00

377 lines
8.9 KiB
JSON

{
"last_node_id": 9,
"last_link_id": 10,
"nodes": [
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [50, 100],
"size": [350, 100],
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [1],
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": null
},
{
"name": "VAE",
"type": "VAE",
"links": [4],
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": ["sd3.5_large.safetensors"],
"title": "SD3.5 Large Checkpoint Loader"
},
{
"id": 9,
"type": "TripleCLIPLoader",
"pos": [50, 250],
"size": [350, 150],
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [9, 10],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "TripleCLIPLoader"
},
"widgets_values": ["clip_l.safetensors", "clip_g.safetensors", "t5xxl_fp16.safetensors"],
"title": "SD3.5 CLIP Loaders (L+G+T5)"
},
{
"id": 2,
"type": "CLIPTextEncode",
"pos": [450, 100],
"size": [400, 200],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 9
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [5],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": ["A beautiful mountain landscape at sunset, highly detailed, professional photography, cinematic lighting, 8k ultra HD, photorealistic"],
"title": "API Positive Prompt"
},
{
"id": 3,
"type": "CLIPTextEncode",
"pos": [450, 350],
"size": [400, 200],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 10
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [6],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": ["blurry, low quality, distorted, watermark, text, signature, ugly, cartoon, painting"],
"title": "API Negative Prompt"
},
{
"id": 4,
"type": "EmptyLatentImage",
"pos": [450, 600],
"size": [315, 106],
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [7],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [1024, 1024, 1],
"title": "API Latent Image Config"
},
{
"id": 5,
"type": "KSampler",
"pos": [900, 100],
"size": [315, 474],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 1
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 5
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 6
},
{
"name": "latent_image",
"type": "LATENT",
"link": 7
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [8],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [42, "fixed", 28, 4.5, "dpmpp_2m", "karras", 1],
"title": "SD3.5 Sampler (28 steps)"
},
{
"id": 6,
"type": "VAEDecode",
"pos": [1270, 100],
"size": [210, 46],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 8
},
{
"name": "vae",
"type": "VAE",
"link": 4
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [2, 3],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"title": "VAE Decode"
},
{
"id": 7,
"type": "PreviewImage",
"pos": [1530, 100],
"size": [400, 400],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 2
}
],
"properties": {
"Node name for S&R": "PreviewImage"
},
"title": "Preview Output"
},
{
"id": 8,
"type": "SaveImage",
"pos": [1530, 550],
"size": [400, 100],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 3
}
],
"properties": {
"Node name for S&R": "SaveImage"
},
"widgets_values": ["sd35_large_output"],
"title": "API Image Output"
}
],
"links": [
[1, 1, 0, 5, 0, "MODEL"],
[2, 6, 0, 7, 0, "IMAGE"],
[3, 6, 0, 8, 0, "IMAGE"],
[4, 1, 2, 6, 1, "VAE"],
[5, 2, 0, 5, 1, "CONDITIONING"],
[6, 3, 0, 5, 2, "CONDITIONING"],
[7, 4, 0, 5, 3, "LATENT"],
[8, 5, 0, 6, 0, "LATENT"],
[9, 9, 0, 2, 0, "CLIP"],
[10, 9, 0, 3, 0, "CLIP"]
],
"groups": [],
"config": {},
"extra": {
"workflow_info": {
"name": "Stable Diffusion 3.5 Large Text-to-Image Production",
"version": "1.2.0",
"description": "Latest generation text-to-image using Stable Diffusion 3.5 Large (28 steps). Provides excellent photorealism and prompt adherence.",
"category": "text-to-image",
"tags": ["sd3.5", "stable-diffusion", "large", "production", "t2i", "photorealistic"],
"requirements": {
"models": ["SD3.5-large", "CLIP-L", "CLIP-G", "T5-XXL FP16"],
"custom_nodes": [],
"vram_min": "18GB",
"vram_recommended": "24GB"
},
"parameters": {
"prompt": {
"node_id": 2,
"widget_index": 0,
"type": "string",
"required": true,
"default": "A beautiful mountain landscape at sunset",
"description": "Text description of desired image"
},
"negative_prompt": {
"node_id": 3,
"widget_index": 0,
"type": "string",
"required": false,
"default": "blurry, low quality",
"description": "Undesired elements to avoid"
},
"width": {
"node_id": 4,
"widget_index": 0,
"type": "integer",
"required": false,
"default": 1024,
"min": 512,
"max": 2048,
"description": "Image width in pixels"
},
"height": {
"node_id": 4,
"widget_index": 1,
"type": "integer",
"required": false,
"default": 1024,
"min": 512,
"max": 2048,
"description": "Image height in pixels"
},
"seed": {
"node_id": 5,
"widget_index": 0,
"type": "integer",
"required": false,
"default": 42,
"min": 0,
"max": 4294967295,
"description": "Random seed for reproducibility"
},
"steps": {
"node_id": 5,
"widget_index": 2,
"type": "integer",
"required": false,
"default": 28,
"min": 20,
"max": 50,
"description": "Number of sampling steps (28 recommended for SD3.5)"
},
"cfg": {
"node_id": 5,
"widget_index": 3,
"type": "float",
"required": false,
"default": 4.5,
"min": 1.0,
"max": 15.0,
"description": "Classifier-free guidance scale (4.5 recommended)"
}
},
"outputs": {
"image": {
"node_id": 8,
"type": "image",
"format": "PNG",
"resolution": "1024x1024 (configurable)"
}
},
"performance": {
"avg_generation_time": "35-45 seconds",
"vram_usage": "~18-20GB",
"gpu_utilization": "95-100%"
},
"notes": [
"SD3.5 uses CheckpointLoaderSimple for MODEL+VAE",
"TripleCLIPLoader loads CLIP-L, CLIP-G, and T5-XXL separately",
"Checkpoint file doesn't include CLIP encoders",
"All three CLIP encoders required for best quality"
]
}
},
"version": 0.4
}