search

Sherrylone / PQDiff

[ICLR 2024] Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach Link: https://arxiv.org/abs/2401.15652
71 stars 1 forks source link

Image size #9

Closed yxWu777 closed 7 months ago

yxWu777 commented 7 months ago

Hello, according to the UViT network in the code, if the image size during training and output can only be the shape of (192，192)? But in the article, I remembered that we can denote a (w, h) as the predefined resolution to be generated. Can this be achieved without adjusting the network structure? Thank you so much for your reply.

Sherrylone commented 7 months ago

Thanks for your interest. Currently, PQDiff only supports fixed-resolution outpainting.

yxWu777 commented 7 months ago

Thank you so much.