MMVID
MMVID copied to clipboard
[CVPR 2022] Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
The whole dataset processed is so huge. Could you please offer a demo or test data image dir?
May I know what is the best way to download the training data? It is very huge (~270G). I tried gdown, but it tells that Access denied with the following...
Hi there @phymhan, Thx for sharing the code. I just found that the [link](https://github.com/phymhan/MMVID/blob/master/mm_vox_celeb/make_text.py) provided for generating texts is broken. Hope it can be fixed.
How to change multi-card distributed training to single GPU training, and the environment is windows
amazing work, can you please add a colab to test this.
Thanks for your inspiring article. When I test the **text_wo_video** task, why does the program still need to read the **video** folder? Can **text_to_video** task generate videos from text alone...