Also on CivitAI

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:

GGUF versions require a custom node to work in comfy:

BNB versions (NF4, FP4) require a custom node to work in comfy:


Downloads last month
1,019
GGUF
Model size
11.9B params
Architecture
flux

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.