Earlier quoted context omitted.
Good on you. I've laughed at many dumbass gags but I've only been a passive consumer of them.
Become the dumbass change you want to see in the world
I'm not nearly creative enough.
Moebius: 0.2B image inpainting model with 10B-level performance
81–86 of 86 posts
Re: Moebius: 0.2B image inpainting model with 10B-level performance
#82Not great. The inpainted areas are, as usual, very smooth compared to the detailed, "high frequency" look of natural photos. Barely useful enough to erase things in thumbnails.
This and these are cherry-picked examples. The one removing that high tension wire in the nature photo is especially bad. You can literally see the band where it erased it. Even the standard restore tool in Photoshop from years ago can do a comparable job.
Re: Moebius: 0.2B image inpainting model with 10B-level performance
#83Earlier quoted context omitted.
Like this? https://huggingface.co/spaces/multimodalart/Moebius
Were you able to make it work? It never works in my case.
https://simonw.github.io/moebius-web/
choose "samlple image" or upload something
then mark something with the mouse (and press 'run inpaint') and it'll work a bit and try to hide it, sorta like that "magic eraser" some newer android phones have
Re: Moebius: 0.2B image inpainting model with 10B-level performance
#84This is the useful AI stuf. There’s so many usecases this makes possible.
how many times have you edited a photo you took on your phone in the last 7 days?
Some smartphones have a feature that detects if you're taking a picture of a menu/letter/etc and will automatically crop and unskew it for you.
Re: Moebius: 0.2B image inpainting model with 10B-level performance
#85Earlier quoted context omitted.
You just refuse to see certain people’s hopes and fears because they didn’t express them in a way you personally find pleasing. The LLMs didn’t prompt themselves.
> The LLMs didn’t prompt themselves. I refuse to accept that real humans believe prompting is art.
Prompting is to coded 2d/3d art what ZBrush is to Blender. If you believe an OpenSCAD construct can be artistic, then it must be the case for prompting, too.
Re: Moebius: 0.2B image inpainting model with 10B-level performance
#86Earlier quoted context omitted.
Perhaps. I like the idea that a piece of art, in addition of ultimately ending up as pixels on my screen, is also a window into a world that has been dreamt up by real human imagination, driven by their hopes and fears. Semiconductors based generation may give me the first part, but not the second. I'm speaking for myself here, I agree with your point though.
> I like the idea that a piece of art, in addition of ultimately ending up as pixels on my screen, is also a window into a world that has been dreamt up by real human imagination, driven by their hopes and fears. I guess this actually defines the fringe between ai-art enjoyers and haters - some people prefer what art does to their imagination, while others look at what art does to others'
Going further, the latter perspective may not even be about "what art doe to others", but about being able to talk about it.
This friction has been present for a long time, probably since before printed media, and way before anyone had any notions about generative AI. You can see it particularly clearly at the border between pop-culture and nerd world. Think of works like, e.g. "Harry Potter", "Lord of the Rings", or "Game of Thrones" - hugely popular, but you have two distinct groups that don't mix well: people who enjoy the work of fiction for its intrinsic characteristics (like lore/worldbuilding), vs. people who enjoy it as social object, giving a different flavor to the daily socializing with friends. Nerds vs. Normies, if you like. They talk past each other a lot.