support HunyuanVideo

TeaCache4HunyuanVideo/README.md

@@ -48,8 +48,41 @@ torchrun --nproc_per_node=8 teacache_sample_video.py \
     --save-path ./teacache_results
 ```
 
+For FP8 inference, you must explicitly specify the FP8 weight path. For example, to generate a video with fp8 weights, you can use the following command:
+
+```bash
+cd HunyuanVideo
+
+DIT_CKPT_PATH={PATH_TO_FP8_WEIGHTS}/{WEIGHT_NAME}_fp8.pt
+
+python3 teacache_sample_video.py \
+    --dit-weight ${DIT_CKPT_PATH} \
+    --video-size 1280 720 \
+    --video-length 129 \
+    --infer-steps 50 \
+    --prompt "A cat walks on the grass, realistic style." \
+    --seed 42 \
+    --embedded-cfg-scale 6.0 \
+    --flow-shift 7.0 \
+    --flow-reverse \
+    --use-cpu-offload \
+    --use-fp8 \
+    --save-path ./teacache_fp8_results
+```
+
+## 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 [HunyuanVideo](https://github.com/Tencent/HunyuanVideo).
+We would like to thank the contributors to the [HunyuanVideo](https://github.com/Tencent/HunyuanVideo).