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

(hustvl.github.io)

103 points | by DSemba 3 hours ago

7 comments

  • delis-thumbs-7e 30 minutes ago
    This is the useful AI stuf. There’s so many usecases this makes possible.
    • doctorpangloss 20 minutes ago
      how many times have you edited a photo you took on your phone in the last 7 days?
      • stusmall 3 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.
      • dogomatic 12 minutes ago
        [dead]
  • GL26 23 minutes ago
    Could this run locally on a smartphone ?
  • teroshan 2 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 1 hour ago
      Scared why?
      • teroshan 1 hour 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 42 minutes 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.
          • solid_fuel 17 minutes ago
            > 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.

            • TeMPOraL 12 minutes ago
              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.

  • NooneAtAll3 2 hours ago
    I don't understand. Is it available somewhere to try or is it just an ad?
  • N_Lens 2 hours ago
    The gallery of their samples is pretty impressive!
  • epolanski 2 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 38 minutes 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 0 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 1 hour 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 1 hour ago
        NB2 means "Nano Banana 2", a Google image generation model. https://blog.google/innovation-and-ai/technology/ai/nano-ban...
      • IAmGraydon 1 hour 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 55 minutes ago
      flux klein with LoRa. GPT image and nano often produce high frequency artifacts when editing.
  • zb3 1 hour ago
    1) What are RAM requirements?

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