FastVideo is a lightweight framework for accelerating large video diffusion models.
https://github.com/user-attachments/assets/5fbc4596-56d6-43aa-98e0-da472cf8e26c
🤗 FastMochi | 🤗 FastHunyuan | 🔍 Discord
FastVideo currently offers: (with more to come)
- FastHunyuan and FastMochi: consistency distilled video diffusion models for 8x inference speedup.
- First open distillation recipes for video DiT, based on PCM.
- Support distilling/finetuning/inferencing state-of-the-art open video DiTs: 1. Mochi 2. Hunyuan.
- Scalable training with FSDP, sequence parallelism, and selective activation checkpointing, with near linear scaling to 64 GPUs.
- Memory efficient finetuning with LoRA, precomputed latent, and precomputed text embeddings.
Dev in progress and highly experimental.
Change Log
2024/12/17:FastVideov0.1 is released.
🔧 Installation
The code is tested on Python 3.10.0, CUDA 12.1 and H100.
./env_setup.sh fastvideo
🚀 Inference
We recommend using a GPU with 80GB of memory. To run the inference, use the following command:
FastMochi
# Download the model weight
python scripts/huggingface/download_hf.py --repo_id=FastVideo/FastMochi-diffusers --local_dir=data/FastMochi-diffusers --repo_type=model
# CLI inference
bash scripts/inference/inference_mochi_sp.sh
FastHunyuan
# Download the model weight
python scripts/huggingface/download_hf.py --repo_id=FastVideo/FastHunyuan --local_dir=data/FastHunyuan --repo_type=model
# CLI inference
sh scripts/inference/inference_hunyuan.sh
You can also inference FastHunyuan in the official Hunyuan github.
More Demos
https://github.com/user-attachments/assets/064ac1d2-11ed-4a0c-955b-4d412a96ef30
Distillation
Please refer to the distillation guide.
Finetuning
Please refer to the finetuning guide.
Acknowledgement
We learned and reused code from the following projects: PCM, diffusers OpenSoraPlan, and xDiT.
We thank MBZUAI and Anyscale for their support throughout this project.