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

123

DDSemba about 4 hours ago 29 commentsRead Article on hustvl.github.io

ES version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

69% Positive

Analyzed from 593 words in the discussion.

Discussion (29 Comments)Read Original on HackerNews

james2doyle•28 minutes ago

There are some demo spaces using this. This one seems the best (paint your own mask) but it failed on all the images I tried: https://huggingface.co/spaces/multimodalart/Moebius

delis-thumbs-7e•about 1 hour ago

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

doctorpangloss•about 1 hour ago

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

stusmall•43 minutes ago

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.

TeMPOraL•18 minutes ago

Half a dozen at least.

(I'm counting only times I used generative editing options in my Galaxy phone - if I were to take your question literally, it would be "at least once every other day", simply due to rotating and cropping.)

dogomatic•about 1 hour ago

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

hari1123•19 minutes ago

lot of the photo editors on mobiles have this, maybe even some apps?

gspr•31 minutes ago

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.

NooneAtAll3•about 3 hours ago

I don't understand. Is it available somewhere to try or is it just an ad?

owebmaster•about 3 hours ago

Yeah it's great but how do I use it?

Edit: I think I found it https://huggingface.co/hustvl/Moebius

K0IN•about 3 hours ago

with this size we could have a interaactive web demo.

james2doyle•40 minutes ago

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

GL26•about 1 hour ago

Could this run locally on a smartphone ?

rasz•36 minutes ago

It sure has a thing for chins, jaws and removing weight, looksmaxing build in.

teroshan•about 3 hours ago

Unrelated but when I read inpainting and Moebius I was scared it was related and using the art of the great Jean Giraud [0] a.k.a. Moebius

https://characterdesignreferences.com/artist-of-the-week-3/m...

[0] https://en.wikipedia.org/wiki/Jean_Giraud

coldtea•about 2 hours ago

Scared why?

teroshan•about 2 hours ago

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.

TeMPOraL•about 1 hour ago

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.

N_Lens•about 3 hours ago

The gallery of their samples is pretty impressive!

epolanski•about 3 hours ago

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.

TeMPOraL•about 1 hour ago

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?

jdiff•41 minutes ago

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.

vunderba•about 2 hours ago

Proprietary? Either gpt-image-2 or NB2.

I have an example of interior decorating inpainting where I replaced a large floor-to-ceiling window with a mirror, and the result was pretty impressive using NB Pro from nearly a year ago.

https://imgpb.com/ZXkiXV

Locally hostable? For my money I'd argue Flux.2 Klein but Qwen-Edit still puts in the work.

CharlesW•about 2 hours ago

NB2 means "Nano Banana 2", a Google image generation model. https://blog.google/innovation-and-ai/technology/ai/nano-ban...

IAmGraydon•about 2 hours ago

As far as I know, gpt-image-2 doesn't even let you define a mask unless you've already run it through one iteration, and once you do define the mask, it just ignores it 90% of the time. It's utterly useless for inpainting. Also, this and other proprietary models are severely limited in their output resolution.

I do agree, however, that the Flux2 family is the SoTA at the moment. Running locally via something like Comfy gets incredible results.

BoredPositron•about 2 hours ago

flux klein with LoRa. GPT image and nano often produce high frequency artifacts when editing.

zb3•about 2 hours ago

1) What are RAM requirements?

2) If these are reasonable, a WebGPU demo would be great..