Moebius: 0.2B image inpainting model with 10B-level performance (hustvl.github.io)
99 points by DSemba 4 hours ago
delis-thumbs-7e 24 minutes ago
This is the useful AI stuf. There’s so many usecases this makes possible.
doctorpangloss 14 minutes ago
how many times have you edited a photo you took on your phone in the last 7 days?
GL26 18 minutes ago
Could this run locally on a smartphone ?
teroshan 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...
coldtea 2 hours ago
Scared why?
teroshan an 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 37 minutes ago
NooneAtAll3 2 hours ago
I don't understand. Is it available somewhere to try or is it just an ad?
owebmaster 2 hours ago
Yeah it's great but how do I use it?
Edit: I think I found it https://huggingface.co/hustvl/Moebius
K0IN 2 hours ago
with this size we could have a interaactive web demo.
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 32 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?
vunderba an 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.
Locally hostable? For my money I'd argue Flux.2 Klein but Qwen-Edit still puts in the work.
CharlesW an hour ago
NB2 means "Nano Banana 2", a Google image generation model. https://blog.google/innovation-and-ai/technology/ai/nano-ban...
IAmGraydon an 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 an hour ago
flux klein with LoRa. GPT image and nano often produce high frequency artifacts when editing.
zb3 2 hours ago
1) What are RAM requirements?
2) If these are reasonable, a WebGPU demo would be great..