Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Moebius: 0.2B image inpainting model with 10B-level performance

hustvl.github.io

Post reply on HN
Print view View original

21–30 of 86 posts

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#21

Post by solid_fuel »

TeMPOraL wrote: post #16
teroshan wrote: post #11

Earlier quoted context omitted.

Scared for the same reason I found last year's 'Ghibli filter' craze upsetting, I would have personally hated to have seen this artist's legacy used for promoting AI image generation.

In case that happened then the rest of the world would probably appreciate the art, and a subset of it, the artist (and even a small subset of ~whole Internet-connected population is a lot of people ). Some silver lining, perhaps.

> In case that happened then the rest of the world would probably appreciate the art

What art?

We’re talking about generated pictures, aka slop, not art made by a real human.

And I don’t know if you’ve been paying attention but people seem to be pretty tired of the slop. I don’t think it would be appreciated nearly as much as you think.

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#22

Post by TeMPOraL »

solid_fuel wrote: post #21
TeMPOraL wrote: post #16

Earlier quoted context omitted.

In case that happened then the rest of the world would probably appreciate the art, and a subset of it, the artist (and even a small subset of ~whole Internet-connected population is a lot of people ). Some silver lining, perhaps.

> In case that happened then the rest of the world would probably appreciate the art What art? We’re talking about generated pictures, aka slop, not art made by a real human. And I don’t know if you’ve been paying attention but people seem to be pretty tired of the slop. I don’t think it would be appreciated nearly as much as you think.

This definition of "slop" doesn't cut reality just quite at the joints.

People are tired of marketing. AI generated slop people are annoyed with, is garbage produced for marketing reasons, and it's distinctly noticeable precisely because all the bottom-feeder marketing houses switched to using it. But it's not the AI itself that's the problem here. Slop was here before, but it was made with cheap protein-based image generators. Silicon-based generators are just cheaper.

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#23

Post by dogomatic »

doctorpangloss wrote: post #20
delis-thumbs-7e wrote: post #18

This is the useful AI stuf. There’s so many usecases this makes possible.

how many times have you edited a photo you took on your phone in the last 7 days?

Personally, about 9 times. Would be higher if it was even easier and cheaper

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#24

Post by stusmall »

doctorpangloss wrote: post #20
delis-thumbs-7e wrote: post #18

This is the useful AI stuf. There’s so many usecases this makes possible.

how many times have you edited a photo you took on your phone in the last 7 days?

I think 3? I feel like that's often enough. Sometimes it's nice to do a quick dumb ass gag on a whim. If I am anything I am a man who loves a dumb ass gag.

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#25

Post by jdiff »

TeMPOraL wrote: post #17
epolanski wrote: post #7

What is the current SOTA for impainting? 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.

Awnings, if I understand correctly (I just learned this word right now), are purely additive attachments to structure exteriors - so perhaps they wouldn't necessarily need a full inpainting model? Wouldn't it be enough to estimate an affine transform for a quad and blend the image of awning directly (and the same with shadow map to fake shade)? Is classical photogrammetry up to such task these days?

I'm quite perplexed by this comment. If I'm understanding you correctly, sure, what you describe is possible through significantly more effort, orchestration, and source photos. Or we can grab one still image and throw an inpainting model at it.

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#26

Post by james2doyle »

K0IN wrote: post #6
owebmaster wrote: post #5

Earlier quoted context omitted.

Yeah it's great but how do I use it? Edit: I think I found it https://huggingface.co/hustvl/Moebius

with this size we could have a interaactive web demo.

Like this? https://huggingface.co/spaces/multimodalart/Moebius

Re: Moebius: 0.2B image inpainting model with 10B-level performance

#28

Post by gspr »

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.

Post reply on HN