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.
Description
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.
Details
Downloads
922
Platform
CivitAI
Platform Status
Available
Created
8/27/2024
Updated
9/27/2025
Deleted
-
Files
Hyper-FLUX.1-dev-16steps-lora.safetensors
Mirrors
Huggingface (1 mirrors)