bcmi / DCI-VTON-Virtual-Try-On

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.
https://arxiv.org/abs/2308.06101
MIT License
387 stars 56 forks source link

How much gpu memory is required to train the diffusion model? #28

Closed bigcornflake closed 10 months ago

bigcornflake commented 10 months ago

Hi thanks for your work. I want to train a 1024 resolution diffusion model. Could you tell me how much GPU memory is needed to train this model?

Limbor commented 10 months ago

In our experiments, we used the A100 80G to train the model of 1024 resolution.

24thTinyGiant commented 9 months ago

@Limbor did you train it on Google Colab orany other device , because I'm running the test.py file but getting error , i folloewd the instructions given in the readme file but then also some errors are coming in running it on google colab. Please Help