search

sail-sg / MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)
Apache License 2.0
500 stars 35 forks source link

High resolution training #4

Closed Junhyuk93 closed 6 months ago

Junhyuk93 commented 1 year ago

Hello,

Thank you for sharing this amazing paper.!! I was wondering if you have tested the model on high-resolution images (e.g., 512x512 or 1024x1024)? Have you encountered any challenges or limitations in applying the model to such high-resolution images?

gasvn commented 1 year ago

Thanks for your interest in our work. For now, we only train the model with 256x256 resolution. I support the larger training cost on high resolution image is the main problem we are facing.