AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset

This repository contains the pre-trained weights of AccVideo. AccVideo is a novel efficient distillation method to accelerate video diffusion models with synthetic datset. Our method is 8.5x faster than HunyuanVideo.

🔥🔥🔥 News

Mar, 2025: We release the inference code and model weights of AccVideo.

📑 Open-source Plan

Inference
Checkpoints
Multi-GPU Inference
Synthetic Video Dataset, SynVid
Training

🔧 Installation

The code is tested on Python 3.10.0, CUDA 11.8 and A100.

conda create -n accvideo python==3.10.0
conda activate accvideo

pip install torch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt
pip install flash-attn==2.7.3 --no-build-isolation
pip install "huggingface_hub[cli]"

🤗 Checkpoints

To download the checkpoints, use the following command:

# Download the model weight
huggingface-cli download aejion/AccVideo --local-dir ./ckpts

🚀 Inference

We recommend using a GPU with 80GB of memory. To run the inference, use the following command:

export MODEL_BASE=./ckpts
python sample_t2v.py \
    --height 544 \
    --width 960 \
    --num_frames 93 \
    --num_inference_steps 50 \
    --guidance_scale 1 \
    --embedded_cfg_scale 6 \
    --flow_shift 7 \
    --flow-reverse \
    --prompt_file ./assets/prompt.txt \
    --seed 1024 \
    --output_path ./results/accvideo-544p \
    --model_path ./ckpts \
    --dit-weight ./ckpts/accvideo-t2v-5-steps/diffusion_pytorch_model.pt

The following table shows the comparisons on inference time using a single A100 GPU:

Model	Setting(height/width/frame)	Inference Time(s)
HunyuanVideo	720px1280px129f	3234
Ours	720px1280px129f	380(8.5x faster)
HunyuanVideo	544px960px93f	704
Ours	544px960px93f	91(7.7x faster)

🔗 BibTeX

If you find AccVideo useful for your research and applications, please cite using this BibTeX:

@article{zhang2025accvideo,
    title={AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset},
    author={Zhang, Haiyu and Chen, Xinyuan and Wang, Yaohui and Liu, Xihui and Wang, Yunhong and Qiao, Yu},
    journal={arXiv preprint arXiv:2503.19462},
    year={2025}
}

Acknowledgements

The code is built upon FastVideo and HunyuanVideo, we thank all the contributors for open-sourcing.