Views
No views yet
git clone https://github.com/alibaba-yuanjing-aigclab/ViViD
cd ViViDconda create -n vivid python=3.10
conda activate vivid
conda activate /mnt/pfs-mc0p4k/ssai/cvg/team/envs/vivid
pip install -r requirements.txt ./ckpts. If you put them somewhere else, you just need to update the path in ./configs/prompts/*.yaml.cd ckpts
git lfs install
git clone https://huggingface.co/lambdalabs/sd-image-variations-diffusersgit lfs install
git clone https://huggingface.co/stabilityai/sd-vae-ft-msegit lfs install
git clone https://huggingface.co/alibaba-yuanjing-aigclab/ViViD./configs/prompts/, run the following commands to have a try😼.python vivid.py --config ./configs/prompts/upper1.yaml
python vivid.py --config ./configs/prompts/lower1.yaml./data, the following data should be provided.1./data/
2|-- agnostic
3| |-- video1.mp4
4| |-- video2.mp4
5| ...
6|-- agnostic_mask
7| |-- video1.mp4
8| |-- video2.mp4
9| ...
10|-- cloth
11| |-- cloth1.jpg
12| |-- cloth2.jpg
13| ...
14|-- cloth_mask
15| |-- cloth1.jpg
16| |-- cloth2.jpg
17| ...
18|-- densepose
19| |-- video1.mp4
20| |-- video2.mp4
21| ...
22|-- videos
23| |-- video1.mp4
24| |-- video2.mp4
25| ..../tools/sam_agnostic.py for an example)1@misc{fang2024vivid,
2 title={ViViD: Video Virtual Try-on using Diffusion Models},
3 author={Zixun Fang and Wei Zhai and Aimin Su and Hongliang Song and Kai Zhu and Mao Wang and Yu Chen and Zhiheng Liu and Yang Cao and Zheng-Jun Zha},
4 year={2024},
5 eprint={2405.11794},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV}
8 }