JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-04-06 03:57:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

update reference

Browse Source
This commit is contained in:
zR 2024-08-15 22:48:24 +08:00
parent 1af3e5bfc4
commit 3917928aba
4 changed files with 16 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -219,14 +219,11 @@ hands-on practice on text-to-video generation. *The original input is in Chinese
🌟 If you find our work helpful, please leave us a star and cite our paper.
```
@misc{yang2024cogvideoxtexttovideodiffusionmodels,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Zhuoyi Yang and Jiayan Teng and Wendi Zheng and Ming Ding and Shiyu Huang and Jiazheng Xu and Yuanming Yang and Wenyi Hong and Xiaohan Zhang and Guanyu Feng and Da Yin and Xiaotao Gu and Yuxuan Zhang and Weihan Wang and Yean Cheng and Ting Liu and Bin Xu and Yuxiao Dong and Jie Tang},
year={2024},
eprint={2408.06072},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2408.06072},
@article{yang2024cogvideox,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
journal={arXiv preprint arXiv:2408.06072},
year={2024}
}
@article{hong2022cogvideo,
title={CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers},

13
README_ja.md
View File

@ -211,14 +211,11 @@ CogVideoのデモは [https://models.aminer.cn/cogvideo](https://models.aminer.c
🌟 私たちの仕事が役立つと思われた場合、ぜひスターを付けていただき、論文を引用してください。
```
@misc{yang2024cogvideoxtexttovideodiffusionmodels,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Zhuoyi Yang and Jiayan Teng and Wendi Zheng and Ming Ding and Shiyu Huang and Jiazheng Xu and Yuanming Yang and Wenyi Hong and Xiaohan Zhang and Guanyu Feng and Da Yin and Xiaotao Gu and Yuxuan Zhang and Weihan Wang and Yean Cheng and Ting Liu and Bin Xu and Yuxiao Dong and Jie Tang},
year={2024},
eprint={2408.06072},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2408.06072},
@article{yang2024cogvideox,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
journal={arXiv preprint arXiv:2408.06072},
year={2024}
}
@article{hong2022cogvideo,
title={CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers},

13
README_zh.md
View File

@ -191,14 +191,11 @@ CogVideo的demo网站在[https://models.aminer.cn/cogvideo](https://models.amine
🌟 如果您发现我们的工作有所帮助，欢迎引用我们的文章，留下宝贵的stars
```
@misc{yang2024cogvideoxtexttovideodiffusionmodels,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Zhuoyi Yang and Jiayan Teng and Wendi Zheng and Ming Ding and Shiyu Huang and Jiazheng Xu and Yuanming Yang and Wenyi Hong and Xiaohan Zhang and Guanyu Feng and Da Yin and Xiaotao Gu and Yuxuan Zhang and Weihan Wang and Yean Cheng and Ting Liu and Bin Xu and Yuxiao Dong and Jie Tang},
year={2024},
eprint={2408.06072},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2408.06072},
@article{yang2024cogvideox,
title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
journal={arXiv preprint arXiv:2408.06072},
year={2024}
}
@article{hong2022cogvideo,
title={CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers},

2
sat/finetune_multi_gpus.sh
View File

@ -2,7 +2,7 @@
echo "RUN on `hostname`, CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
run_cmd="torchrun --standalone --nproc_per_node=4 train_video.py --base configs/cogvideox_2b_sft.yaml --seed $RANDOM“
run_cmd="torchrun --standalone --nproc_per_node=4 train_video.py --base configs/cogvideox_2b_sft.yaml --seed $RANDOM"
echo ${run_cmd}
eval ${run_cmd}