Readme
About
This is a Cog implementation of the ByteDance/Hyper-SD Flux.1-Dev 8-step LoRA
This LoRA was uploaded via the unique feature of the model
ostris/flux-dev-lora-trainer
. To create a Replicate model from a pre-trained LoRA that’s on HuggingFace, use the
skip_training_and_use_pretrained_hf_lora_url
parameter at the bottom
News
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
Official Repository of the paper: Hyper-SD .
Project Page: https://hyper-sd.github.io/
Try our Hugging Face demos:
Hyper-SD Scribble demo host on 🤗 scribble
Hyper-SDXL One-step Text-to-Image demo host on 🤗 T2I
Introduction
Hyper-SD is one of the new State-of-the-Art diffusion model acceleration techniques. In this repository, we release the models distilled from FLUX.1-dev , SD3-Medium , SDXL Base 1.0 and Stable-Diffusion v1-5 。
Checkpoints
-
Hyper-FLUX.1-dev-Nsteps-lora.safetensors: Lora checkpoint, for FLUX.1-dev-related models. -
Hyper-SD3-Nsteps-CFG-lora.safetensors: Lora checkpoint, for SD3-related models. -
Hyper-SDXL-Nstep-lora.safetensors: Lora checkpoint, for SDXL-related models. -
Hyper-SD15-Nstep-lora.safetensors: Lora checkpoint, for SD1.5-related models. -
Hyper-SDXL-1step-unet.safetensors: Unet checkpoint distilled from SDXL-Base.
Citation
@misc{ren2024hypersd,
title={Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis},
author={Yuxi Ren and Xin Xia and Yanzuo Lu and Jiacheng Zhang and Jie Wu and Pan Xie and Xing Wang and Xuefeng Xiao},
year={2024},
eprint={2404.13686},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Licensing and commercial use
If you generate images on Replicate with FLUX.1 models and their fine-tunes, then you can use the images commercially.
If you download the weights off Replicate and generate images on your own computer, you can’t use the images commercially.
