RERV/VDT

Issues

• Physion inference with less than 8 condition frames

  #9 opened 8 months ago by aweitz
  5

• Would you release the training code?

  #1 opened a year ago by zen-d
  4

• Training Code and Dataset format?

  #6 opened 9 months ago by BingliangLi
  4

• GPU computer capability

  #11 opened 6 months ago by MeL0XIA
  0

• Question about the `VDT`

  #13 opened 6 months ago by zhang-haojie
  0

• How to make text to video diffusion network?

  #12 opened 7 months ago by ersanliqiao
  1

• 文中的Mask机制，在代码中对不上

  #10 opened 8 months ago by Nutingnon
  2

• test

  #8 opened 8 months ago by gggxxx1234
  2

• 不吹不擂，分析一下VDT和Sora之间的差别，顺Genie继续往远眺望...

  #7 opened 9 months ago by yuedajiong
  0

• any diff with https://github.com/VDT-2023/VDT?

  #5 opened 9 months ago by nemonameless
  1

• More Physion evaluation results

  #4 opened a year ago by DylanTao
  1

• Some confusion about the code.

  #2 opened a year ago by jiangchaokang
  1

• Cityscapes pretrained model

  #3 opened a year ago by JunyaoHu
  1