search

Zheng-Chong / CatVTON

CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) and 3) Simplified Inference (< 8G VRAM for 1024X768 resolution).
Other
951 stars 114 forks source link

Lower inpaint not working #70

Closed Elthibert closed 1 month ago

Elthibert commented 1 month ago

I've tried everything, but i can't find a way to make the model swap pants part. Maybe i'm doing something wrong, but even with precise Segment anything masking + different image resolutions, the input pants image is not transfered in the masked image. But there is no problem for upper body part.

Elthibert commented 1 month ago

well, after some trials it's seems to be due to my original image (the man is wearing a bomber jacket). But when i cange him by a naked upper body,, it works this time.