Glad you enjoyed the technical postmortem!

I agree with what you said, but I think it's reductive for a few reasons:

- It was (and still is) amazing to me that GPT Image 2.0 was this good at making a coherent manga page in one shot.

- This project was focused mainly on the animation pipeline, not the manga page content.

- As with all things AI, it is up to the user's creative direction to make the output good. I did not give much creative direction at all to the example manga page, thus the AI catchphrases. With some guidance, this seems to be a very promising way to get your manga ideas onto "paper" quickly if you desire.

Yeah, I agree, I think specificity is key. If you leave an LLM, or any AI model, to its own devices, it gravitates to the figurative "mean of its training data" which tends to be pretty sterile.

I actually have some examples of my own comics that I used to put gpt-image-2 through its paces, and the results were surprisingly good as well:

https://mordenstar.com/other/gpt-2-comics

Let me know how it goes!

Neat! Glad it's a cognate for cool words haha :)

Very actively developing this project, so hopefully it'll become a suitable replacement relatively soon. Please open GitHub issues or PRs if you have specific requests, happy to help.

Haha glad it brought back fond memories! Grob is just the nickname of my username GroverBurger. Fun coincidence.

Yep, magic wand already exists with contiguous/global toggle and tolerance slider. : )

Thanks! Not sure how I missed that!

It still amazes me that so many people can see LLMs writing code as anything less than a miracle in computing...

I mean, a trained dog who plays the piano is a miracle in canine education, until such a point where you assess the quality of its performance.

This is sick, loved the 2swap video on this. Happy to see more content visualizing lambda calculus and Tromp lambda diagrams.

This is so cool to see. Saw tons of Waymo in LA/Santa Monica area when I was there in October. Very excited to see them expand basically all through SoCal!

Thanks! I appreciate the kind words.

I didn't get around to that because my monitor is not amazingly wide (mainly using a laptop :P). Thanks for the feedback though, I may add that in the future.

That's fair :)