flux-txt2img
Installation
SKILL.md
Flux Text-to-Image Workflows
Overview
Flux is a guidance-distilled diffusion model family from Black Forest Labs. It uses a separate FluxGuidance node instead of KSampler CFG (which must always be 1.0). Three variants are available locally:
- Flux.1 Dev SRPO. Fine-tuned Flux.1 Dev with SRPO alignment. Uses DualCLIPLoader (T5XXL + CLIP-L). BF16 only.
- Flux 2 Klein 9B. Distilled Flux 2 variant. Uses single CLIPLoader (Qwen3-8B) +
flux2-vae.safetensors. Fast 4-step generation. - Flux 2 Turbo LoRA. Applied to Flux.1 Dev for 4-step generation.
Models
Flux.1 Dev SRPO
| Component | Node | Model | Notes |
|---|---|---|---|
| UNET | UNETLoader |
flux.1-dev-SRPO-BFL-bf16.safetensors |
22.7GB, BF16 only — FP8 produces broken results |
| CLIP | DualCLIPLoader (type=flux) |
clip_name1: t5xxl_fp8_e4m3fn.safetensors, clip_name2: clip_l.safetensors |
T5XXL (4.7GB) + CLIP-L (235MB) |
| VAE | VAELoader |
ae.safetensors |
Standard Flux VAE (320MB). Z-Image uses the same VAE architecture but different weights — its VAE is a separate file (z-image-ae.safetensors), not this one |