SHI-Labs / Prompt-Free-Diffusion

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024

Home Page:https://arxiv.org/abs/2305.16223

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Query regarding image resolution for SeeCoder during training

hbin-ac opened this issue · comments

Hello,
I am currently delving into your intriguing SeeCoder, and have a question that I could not find an answer to in the paper. Could you please clarify the resolution of the batch input images used during the training process?