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

owebmaster wrote: post #5

NooneAtAll3 wrote: post #4

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

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.

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

#7

Post by epolanski » Mon, Jun 22, 2026, 3:33 PM UTC

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.

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

#8

Post by zb3 » Mon, Jun 22, 2026, 3:51 PM UTC

1) What are RAM requirements?

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

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

#9

Post by coldtea » Mon, Jun 22, 2026, 3:56 PM UTC

teroshan wrote: post #2

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

Scared why?

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

#10

Post by vunderba » Mon, Jun 22, 2026, 3:59 PM UTC

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.

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.