Merge of Schnell, finetuned Dev and Hyper. Recommended 4-8 steps. Greatly improved quality at 4 steps compared to V1.
Important
All in one versions include VAE + CLIP + T5XXL (fp8).
UNET versions (Model only) need Text Encoders and VAE, downloads:
- Text Encoders: https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
- VAE: https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main/vae
GGUF versions require a custom node to work in comfy:
BNB versions (NF4, FP4) require a custom node to work in comfy:
- All in one versions: https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4
- UNET versions: https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4
- Downloads last month
- 1,103
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.