bytedance / hyper-flux-8step

Hyper FLUX 8-step by ByteDance

  • Public
  • 1.8M runs
  • GitHub
  • Paper
  • License

Run time and cost

This model costs approximately $0.013 to run on Replicate, or 76 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 9 seconds.

Readme

About

This is a Cog implementation of the ByteDance/Hyper-SD Flux.1-Dev 8-step LoRA

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.