HamzahSk/KOMIK-TL ? reverse-engineered prompt

Build me a simple tool that helps translate comic pages or image based panels from one language to another.

I want to be able to give it a batch of images, have it read the text in the speech bubbles, translate that text, and put the translated words back onto the image in a clean way. It should keep the page looking natural, so the text placement and font styling feel close to the original. If it needs to use OCR, image cleanup, or online translation, that’s fine. Look up current docs online if you need to.

Please make it easy to run from a single main script, with a config file for the language and other basic settings. If possible, include a simple way to test it on a few sample images and a small build or run script so I can try the full flow quickly.