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

for video #36

Open zachysaur opened 3 months ago

zachysaur commented 3 months ago

is it possible to use for video?

Zheng-Chong commented 3 months ago

That's still a long way to go 😂

zachysaur commented 3 months ago

i mean for a short video of 100 frames

Zheng-Chong commented 3 months ago

There are some video try-on models, such as VIVID; if you are interested, you might want to look them up. However, overall, video try-on is still a field that awaits further exploration.

zachysaur commented 3 months ago

i have tried many so far yours is best and accurate you should try for video