Excuse me, I noticed that there may be structural issues when there is a hand blocking the front

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

964 stars 114 forks source link

Excuse me, I noticed that there may be structural issues when there is a hand blocking the front #48

Open 807502278 opened 2 months ago

807502278 commented 2 months ago

ComfyUI_temp_amkfp_00001_ ComfyUI_temp_drbkp_00002_

Zheng-Chong commented 2 months ago

It can be challenging for SCHP and DensePose to accurately parse anime characters in complex poses, leading to inaccurately generated masks. You may try manually drawing masks to preserve key exposed body parts such as arms, hands, and neck.