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.
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.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.