wyhsirius / LIA

[ICLR 22] Latent Image Animator: Learning to Animate Images via Latent Space Navigation
https://wyhsirius.github.io/LIA-project/
Other
578 stars 64 forks source link

Fix driving video resolution issue #8

Open BbChip0103 opened 1 year ago

BbChip0103 commented 1 year ago

regarding #6

When we use driving video which have not 256 size, the video will be cropped to 256X256 size (not resizing) So I fixed this issue. Now driving video will be resized by arg.size. And this model is superior to maintain face shape compare than the other face animation models.

Thank you. (BTW, please share 512 size checkpoint. we are anxiously hoping for that)

netuserjun commented 1 year ago

Thank you!