ByteDance Hyper-FLUX Acceleration LoRA

Flux.1 D Standard LORA

ByteDance Hyper-FLUX Acceleration LoRA Hyper-FLUX.1-dev-8steps

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-FLUX.1-dev-8steps-lora.safetensors

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.

Other versions

Hyper-FLUX.1-dev-16steps