kabachuha / infinet Goto Github PK

• Add dataset splitter
• Add a low level clip/image captioner like BLIP2 if the description is not available
• Use an external LLM like OpenAI's ChatGPT or plain GPT-3, or even a local model like LLaMa via APIs to generate descriptions for higher level videos by combining the subclips with a global prompt
• Improve the batching process
• Do a test train

Great work! Have there been any experimental results on integrating it into the Damo Text-to-Video system?

哥们还在维护这个project吗？最近想找开源的NUWA-XL在自己的数据集训练，但是好像这个project维持到一半停了？

https://github.com/kabachuha/overfusion/blob/master/t2v_modules/dod_unet.py#L116-L140

or else we'll lose a lot of compute

Thanks for such an awesome work!
Are there any pre-trained weights available?