Live data from Hacker News

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

hustvl.github.io

11–20 of 86 posts

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

#11
post #9
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?

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.

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

#12

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.

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.

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

#13

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.

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

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

#14

Earlier quoted context omitted.

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.

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 Com…

Yeah definitely. You can do workarounds like drawing circles or using highlighters to create pseudo-masks for use with OpenAI or Google models but it’s really just a visual indication more than anything.

If you want real precision (especially for complex polygonal masks), or if you’re concerned about image degradation over multiple edit rounds, you'll slam against the limitations of those approaches.

Even with SOTA proprietary models, repeatedly editing and re-uploading an image is like making a copy of a copy of a VHS tape: you're gonna see subtle color shifts and quality loss steadily accumulate.

At that point, you either need to put in the manual work in something like Photoshop (bringing elements in as layers and masking them properly) or, as you mentioned, use a model or workflow that properly supports masking.

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

#15

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.

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

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

#16
post #9

Earlier quoted context omitted.

Scared why?

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.

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

#17

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?
Post reply on HN