How can we save pre-processed images as png - what is used during training

I know --debug option but it is very very slow

Are there any option to what is being used in the training? Like when pre-processing images and prompts we can save final used image and the prompt?

Thank you @kohya-ss

The issue names no files, tests, or entry points. Start by locating the training image and prompt preprocessing flow, then clarify the output format and where saved PNGs and prompts should be produced without the slow --debug option.

Written by the indexing model from the issue text.