ByteDance Hyper-FLUX Acceleration LoRA: Hyper-FLUX.1-dev-8steps: Hyper-FLUX.1-dev-8steps-lora.safetensors

Our 8-steps and 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. Lower step LoRAs would be coming soon.

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.