comfyui-workflow

ComfyUI Workflow Guide

Comprehensive guide to building image generation workflows in ComfyUI. Covers SD1.5, SDXL, SD3.5, and Flux model families with all common pipeline patterns.

When to Use This Skill

• Creating text-to-image, image-to-image, or inpainting workflows
• Setting up Flux, SDXL, or SD3.5 pipelines
• Adding ControlNet, LoRA, IPAdapter, or other conditioning
• Optimizing sampler/scheduler settings
• Building complex multi-stage generation pipelines

---

Model Families & Loading

Different models require different loader nodes. This is the most common source of errors.

SD1.5 / SDXL

Uses a single checkpoint file containing UNet + CLIP + VAE.

Node: CheckpointLoaderSimple
  ckpt_name: "sd_xl_base_1.0.safetensors"
Outputs: MODEL, CLIP, VAE

File location: ComfyUI/models/checkpoints/

SD3.5

Uses a checkpoint with triple CLIP (clip_g + clip_l + t5xxl).

Node: CheckpointLoaderSimple
  ckpt_name: "sd3.5_large.safetensors"
Outputs: MODEL, CLIP, VAE

Or load components separately:

Node: UNETLoader
  unet_name: "sd3.5_large.safetensors"
  weight_dtype: "default"
Outputs: MODEL

Node: TripleCLIPLoader
  clip_name1: "clip_g.safetensors"
  clip_name2: "clip_l.safetensors"
  clip_name3: "t5xxl_fp16.safetensors"
Outputs: CLIP

Node: VAELoader
  vae_name: "sd3.5_vae.safetensors"
Outputs: VAE

SD3.5 Variants:

Model	Params	Speed	Quality
SD3.5 Large	8B	Slow	Best
SD3.5 Large Turbo	8B distilled	Fast	Good
SD3.5 Medium	2.5B	Medium	Good

Flux

Flux does NOT use a single checkpoint. Load components separately:

Node: UNETLoader (or "Load Diffusion Model")
  unet_name: "flux1-dev.safetensors"
  weight_dtype: "default"
Outputs: MODEL

Node: DualCLIPLoader
  clip_name1: "t5xxl_fp16.safetensors"    (or fp8)
  clip_name2: "clip_l.safetensors"
  type: "flux"
Outputs: CLIP

Node: VAELoader
  vae_name: "ae.safetensors"
Outputs: VAE

Exception: FP8 checkpoint versions can use CheckpointLoaderSimple with CFG=1.0.