You must log in or # to comment.
Panel 6: how to write gibberish in Japanese
On a more serious note, the concept is fun but the execution ruines it 😟
Koko!
Koko!slop👎
Nope. Not AI, apparently. and there are way more of them in the series than OP posted!
(artist is iron.trung on instagram)
iron.trung use google gemini nano banana 2, look at the bottom right watermarks.
Every single one of these is awesome!
edit: I have discovered more! How wonderful! I love them all!
Artist unknown
There is no artist. It’s slop.
You positive? Doesn’t look like it to me
It looks a lot like it. The text is the biggest giveaway. Then there’s the poses repeated between many different characters. On top of that, the “almost identical but slightly different” settings in each image is an obvious tell of “someone iterated this prompt through different seeds until they got results they liked”.
On the text I’m pretty sure it was AI translated, that was the first thing I noticed because of the 3rd and last panel. You see that a lot in manga due to a lack of translators.
I see what you mean about the settings, not 100% convinced it is AI, but yeah definitely have some doubts on it. It’s unfortunate how much you have to scrutinize content now to figure out if it’s real or AI slop.
Edit: someone pointed out the Gemini logo I completely missed. 🤦♂️
I see what you mean about the settings, not 100% convinced it is AI, but yeah definitely have some doubts on it.
A human made image will have intent in a scene like this. The classrooms could be different, but the similarities will be consistent and the differences will be intentional and have purpose. With generated images, it’s a poorly structured facsimile. It’s actually easier to pic out in series of images like this, because the “this is what a classroom looks like” features exist in each image, but they’re slightly different for no reason - the speaker is lower or shifted to the side, the poster board turns into a cork board, the ceiling changes material at random, etc, etc.
IMO, the more reliable sign in images like this is the poses. Those can be spotted even in singular generations. LIMs can’t do groups of people very realistically (yet), so it ends up repeating poses throughout the image. In the first two images, all the characters are positioned pretty much identically. In the next to, you have can see differences, but even those get repeated elsewhere in the same image. Part of this is a model having similar patterns for “this is the facing forward pose” and “this is the facing right pose” that you’ll see between generations, combined with a tendency for results to have less diversity within individual iterations. If “laughing and pointing” means one thing with a certain seed, it will typically mean that same thing anytime the algorithm results in “laughing and pointing” throughout the image.
It’s unfortunate how much you have to scrutinize content now to figure out if it’s real or AI slop.
It is, and it’s going to get harder. But fwiw, my sole experience with this tech is locally hosted LLMs and LIMs that are necessarily much weaker than the commercial variants (since I don’t have the means or desire to wreck communities and nature to erect heinous numbers of data centers), but even with the admittedly more impressive models, these tells still exist.
The watermark in the lower right of each image is the Gemini watermark. Definitely AI
🤦♂️I didn’t even catch that. Idk how I missed it.
All good - theyre still funny :) . just because they’re AI doesn’t make them bad
Not sure anyone loves the life alchemist from FMA…frankly im upset I was reminded of him.
These are amazing.
Sanji being the only guy in boobs class, Sasuke and Zoro being in marriage class 👌
