[awdii]

Awesome stuff! We're also working on comic segmentation @ https://toona.io and other stuff for motion comic generation. The synthetic dataset approaches are really interesting, I'm curious if you could use an algorithm like https://en.wikipedia.org/wiki/Flood_fill to aid in segmentation (especially for manga).

[matroid]

The original blog post by Max Halford (https://maxhalford.github.io/blog/comic-book-panel-segmentat...) does exactly that. I love his approach because, unlike mine, it is simple, yet it goes a long way. I'd encourage you to check it out.

Can you explain what you mean by motion comic generation? Sounds interesting!

[awdii]

Oh wow I'll check that out! We're basically working on tools for turning normal comics into semi-animated versions with things like puppet animation (similar to live 2d style), and stable diffusion models. A lot of the work for traditional approaches is segmentation and in painting, so that's what we're working on now, but we're also making tools for colorization, effects, and controllable animations!

[matroid]

All that sounds definitely a lot of fun. I was also working on colorization with SD ControlNet recently (https://vrroom.github.io/blog/2024/02/16/interactive-colorin...).

[bigbillheck]

This is, as they say, an insult to life itself.