TeaCache can speedup FLUX 2x without much visual quality degradation, in a training-free manner. The following image shows the results generated by TeaCache-FLUX with various rel_l1_thresh values: 0 (original), 0.25 (1.5x speedup), 0.4 (1.8x speedup), 0.6 (2.0x speedup), and 0.8 (2.25x speedup).
| FLUX.1 [dev] | TeaCache (0.25) | TeaCache (0.4) | TeaCache (0.6) | TeaCache (0.8) |
|---|---|---|---|---|
| ~18 s | ~12 s | ~10 s | ~9 s | ~8 s |
pip install --upgrade diffusers[torch] transformers protobuf tokenizers sentencepieceYou can modify the rel_l1_thresh in line 320 to obtain your desired trade-off between latency and visul quality. For single-gpu inference, you can use the following command:
python teacache_flux.pyIf you find TeaCache is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.
@article{liu2024timestep,
title={Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model},
author={Liu, Feng and Zhang, Shiwei and Wang, Xiaofeng and Wei, Yujie and Qiu, Haonan and Zhao, Yuzhong and Zhang, Yingya and Ye, Qixiang and Wan, Fang},
journal={arXiv preprint arXiv:2411.19108},
year={2024}
}
We would like to thank the contributors to the FLUX and Diffusers.