Comment by diyer22
2 days ago
It's just a coincidence—the guided images used for ZSCG all come from Celeb-A, whereas the DDN model was trained only on FFHQ.
Besides, I feel the red shoulder strap/blob is reconstructed rather poorly.
2 days ago
It's just a coincidence—the guided images used for ZSCG all come from Celeb-A, whereas the DDN model was trained only on FFHQ.
Besides, I feel the red shoulder strap/blob is reconstructed rather poorly.
No comments yet
Contribute on Hacker News ↗