Nitpick: in the showcase on that page, under Comparison of Natural Scenes, Moebius should definitely get a "structural confusion" tag for the back of the surfboard. If other models get deducted for truncating the surfboard, then surely the elongation that Moebius does should count too.
Also, what's going on behind the in-painted corner of the house? We'd need to see higher resolution pictures, but I'm not convinced that it too shouldn't get a flag. Likewise with the beach just behind the surfboard. Not terrible, but what gets flagged in the competitors is similar.
> The core insight of Moebius can be summarized in a single equation:
Synergy × (Architecture + Distillation) = Shattering the "Impossible Triangle" of Low Parameters, Fast Inference, and High Quality
Is it just me or is it weird seeing these clickbaity AI-generated taglines in an otherwise scientific work?
Tried a bit, and while it is very impressive for 0.2B model it would be very hard to convince me that this matches with 10B models. It did work reasonably well with natural images but inpainted regions were visibly smoother than surroundings, and performed very badly on novel objects. It is also limited to 512x512 output, which limits its practical usefulness.
I did an inpainting project for a client a few years ago. They were trying to inpaint banner ads for concert promoters, and find a way to make it easy to produce a bunch of different sized ads for a variety of placements. I was tasked with inpainting Xmas themed ad for a few major singers.
The weirdest thing was when the inpainting tool added strange people to an image. This singer was all decked out in tinsel and red, and the inpainting model added a grumpy old man in a top hat. I don't recall clicking the "Add creepy old man" button.
At the time this was Stable Diffusion on the backend, run by a variety of model hosting services, Amazon being one. They all had different requirements for the input image and that made things really complex. For some the aspect ratio was impossible to meet, and it would fail if the banner was 200x60. For others, you had to resize it before input, which meant you were adding an image with poor resolution to start. Garbage in, garbage out.
All of this to say, there is a lot of preproduction that went into it, and the client never ended up using my attempts.
> At the time this was Stable Diffusion on the backend
The community made models (merges, fine tunes, etc) of that era are all completely overtrained and optimized for portraits and frontal shots. They would try to make a person out of anything. Inpainting faces is already a chore, even with a lot of tooling around that, but inpainting anything else is almost impossible. These models are also especially bad to fit objects naturally into scenes. You can make a crappy necklace or belt work, but introducing a new object into a scene just fails with infinite variety.
They are also much better using 512x512 as resolution, any larger deviation introduces more problems.
Considering you wanted to inpaint banner ads, they would probably get distorted heavily. Those models can't deal with fonts and are bad at a pixel perfect transfers. The only viable way to do this, at that time, would be to manually insert the banner ads and fix the seams with AI. Requires some artistic skill of course.
Your attempt was bold, but with the expectation of just supplying two images and let the models do it, it was impossible.
I want a version of this for manga (for translation). Right now I think the go-to lightweight inpainting model for anime and manga is LaMa which is several years old now and it feels like there is room for improvement.
21 comments
[ 4.3 ms ] story [ 38.1 ms ] threadhttps://characterdesignreferences.com/artist-of-the-week-3/m...
[0] https://en.wikipedia.org/wiki/Jean_Giraud
I have a potential project for my e-commerce where I want to allow users to upload images of their house exteriors and impaint awnings.
2) If these are reasonable, a WebGPU demo would be great..
Also, what's going on behind the in-painted corner of the house? We'd need to see higher resolution pictures, but I'm not convinced that it too shouldn't get a flag. Likewise with the beach just behind the surfboard. Not terrible, but what gets flagged in the competitors is similar.
Is it just me or is it weird seeing these clickbaity AI-generated taglines in an otherwise scientific work?
The weirdest thing was when the inpainting tool added strange people to an image. This singer was all decked out in tinsel and red, and the inpainting model added a grumpy old man in a top hat. I don't recall clicking the "Add creepy old man" button.
At the time this was Stable Diffusion on the backend, run by a variety of model hosting services, Amazon being one. They all had different requirements for the input image and that made things really complex. For some the aspect ratio was impossible to meet, and it would fail if the banner was 200x60. For others, you had to resize it before input, which meant you were adding an image with poor resolution to start. Garbage in, garbage out.
All of this to say, there is a lot of preproduction that went into it, and the client never ended up using my attempts.
The community made models (merges, fine tunes, etc) of that era are all completely overtrained and optimized for portraits and frontal shots. They would try to make a person out of anything. Inpainting faces is already a chore, even with a lot of tooling around that, but inpainting anything else is almost impossible. These models are also especially bad to fit objects naturally into scenes. You can make a crappy necklace or belt work, but introducing a new object into a scene just fails with infinite variety.
They are also much better using 512x512 as resolution, any larger deviation introduces more problems.
Considering you wanted to inpaint banner ads, they would probably get distorted heavily. Those models can't deal with fonts and are bad at a pixel perfect transfers. The only viable way to do this, at that time, would be to manually insert the banner ads and fix the seams with AI. Requires some artistic skill of course.
Your attempt was bold, but with the expectation of just supplying two images and let the models do it, it was impossible.
(Claude Code transcript: https://gisthost.github.io/?58039ba5c1ca3ed177e8659168996ee4)
Wrote this up in more detail on my blog: https://simonwillison.net/2026/Jun/22/porting-moebius/
https://inpaintlab.com/
Barely useful enough to erase things in thumbnails.