search

RQ-Wu / LAMP

Official implement code of LAMP: Learn a Motion Pattern by Few-Shot Tuning a Text-to-Image Diffusion Model (Few-shot-based text-to-video diffusion)
https://rq-wu.github.io/projects/LAMP/index.html
Other
236 stars 10 forks source link

Question about the training time #12

Closed CHNxindong closed 7 months ago

CHNxindong commented 7 months ago

Thanks for your great work! I have a question about the training time: when I train the horse_running in my GPU (RTX 3090 24G), it displays about 14hours for training. I want to know wheather this is normal? image Expecting your reply!

RQ-Wu commented 7 months ago

Thanks for your great work! I have a question about the training time: when I train the horse_running in my GPU (RTX 3090 24G), it displays about 14hours for training. I want to know wheather this is normal? image Expecting your reply!

This is normal, you can increase the intervals of validation to shorten the training time, usually 10k-20k steps will perform well (depending on the difficulty of the motion)

CHNxindong commented 7 months ago

I see. Thanks for your quick reply!