# TeaCache4HiDream-I1 [TeaCache](https://github.com/LiewFeng/TeaCache) can speedup [HiDream-I1](https://github.com/HiDream-ai/HiDream-I1) 2x without much visual quality degradation, in a training-free manner. The following image shows the results generated by TeaCache-HiDream-I1-Full with various `rel_l1_thresh` values: 0 (original), 0.17 (1.5x speedup), 0.25 (1.7x speedup), 0.3 (2.0x speedup), and 0.45 (2.6x speedup).  ## 📈 Inference Latency Comparisons on a Single A100 | HiDream-I1-Full | TeaCache (0.17) | TeaCache (0.25) | TeaCache (0.3) | TeaCache (0.45) | |:-----------------------:|:----------------------------:|:--------------------:|:---------------------:|:--------------------:| | ~50 s | ~34 s | ~29 s | ~25 s | ~19 s | ## Installation ```shell pip install git+https://github.com/huggingface/diffusers pip install --upgrade transformers protobuf tiktoken tokenizers sentencepiece ``` ## Usage You can modify the `rel_l1_thresh` in line 297 to obtain your desired trade-off between latency and visul quality. For single-gpu inference, you can use the following command: ```bash python teacache_hidream_i1.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 [HiDream-I1](https://github.com/HiDream-ai/HiDream-I1) and [Diffusers](https://github.com/huggingface/diffusers).