How to generate a single image after training

Hello,

I have been trying to play with the code a little bit with the intention of creating just a single image instead of an 8X8 grid of images but to no avail. Can somebody point out how to do the same.

Start by reading the repository's training and image-generation flow to determine where the 8×8 grid is produced and whether the post-training generation path is documented. The issue is resolved when the project clearly explains how to generate one image after training, with the relevant command or entry point identified.

Written by the indexing model from the issue text.