TeaCache4Lumina2

TeaCache can speedup Lumina-Image-2.0 without much visual quality degradation, in a training-free manner. The following image shows the results generated by TeaCache-Lumina-Image-2.0 with various rel_l1_thresh values: 0 (original), 0.2 (1.25x speedup), 0.3 (1.5625x speedup), 0.4 (2.0833x speedup), 0.5 (2.5x speedup).

📈 Inference Latency Comparisons on a single 4090 (step 50)

Lumina-Image-2.0	TeaCache (0.2)	TeaCache (0.3)	TeaCache (0.4)	TeaCache (0.5)
~25 s	~20 s	~16 s	~12 s	~10 s

Installation

pip install --upgrade diffusers[torch] transformers protobuf tokenizers sentencepiece
pip install flash-attn --no-build-isolation

Usage

You can modify the thresh in line 154 to obtain your desired trade-off between latency and visul quality. For single-gpu inference, you can use the following command:

python teacache_lumina2.py

Citation

If 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}
}

Acknowledgements

We would like to thank the contributors to the Lumina-Image-2.0 and Diffusers.