Heyis

Hi, great works! I have the version conflict with videogpt and torch. Downloaded the code from VideoGPT, and running pip install -e . But videogpt 1.0 requires torch version ~=1.7,...

I fisrt use VQVAE for video compress, the code runs fine. But Loss drops very slowly. So I change AE to VAE, and I got the OOM error, even though...

How long does it take to finetune the base model (unet + adapter)？Using two V100 images, training the model takes approximately 2000 hours. Is this normal？

Full-parameter finetune后，生成视频的主体空间扭曲

6

您好！非常棒的开源repo~ 最近尝试了Lora和full-parameter的finetune，均使用同样的50个video，微调500次迭代，其余setting没有修改 发现full-parameter的微调后，生成视频的主体会非常扭曲，lora的微调形式没有这种明显扭曲 下面是同样的prompt： spider making a web的结果： full-parameter微调后 https://github.com/user-attachments/assets/19f4f8bb-973c-4b42-9a0c-422c1af29af0 lora微调后 https://github.com/user-attachments/assets/4ab01f8b-8e05-4fbc-b038-a2796c69adfa 不知道导致这一问题的原因是什么？是微调时的lr太高的原因吗？ 期待您的回复，感谢

Cogvideo2B score

8

Hi, I see that the total score of cogvideo2B on Leaderboard is 80.94%, but after I use all_dimension_long. txt to inference, the total score measured is only 78.68%. The video...