ByteDance Hyper-FLUX LoRA

16-steps FLUX.1-dev-related LoRAs are available now! We recommend LoRA scales around 0.125 that is adaptive with training and guidance scale could be kept on 3.5.

Hyper-SD is one of the new State-of-the-Art diffusion model acceleration techniques.

For more information, please refer to https://huggingface.co/ByteDance/Hyper-SD.