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

(hustvl.github.io)

67 points | by DSemba 2 hours ago

5 comments

  • teroshan 1 hour 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 33 minutes ago
      Scared why?
      • teroshan 13 minutes 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.
  • NooneAtAll3 1 hour ago
    I don't understand. Is it available somewhere to try or is it just an ad?
  • epolanski 57 minutes 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.

    • vunderba 31 minutes 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 3 minutes ago
        NB2 means "Nano Banana 2", a Google image generation model. https://blog.google/innovation-and-ai/technology/ai/nano-ban...
      • IAmGraydon 4 minutes 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.

  • N_Lens 1 hour ago
    The gallery of their samples is pretty impressive!
  • zb3 38 minutes ago
    1) What are RAM requirements?

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