21–30 of 86 posts
The title excited me - maybe someone succeeded making new art that looks like the old pre-renders, maybe a convincing imitation of the scanline render look. Instead it was a vapid article about tossing pixel art into img-2-img and getting some tenuously related junk.
[flagged]
[flagged]
I have a question. Stable diffusion is based on gradually processing noise into a coherent image, by training a denoiser. Would it be possible to feed low-fidelity image (such as pixel art, or pixelated image) directly into the denoiser step and get a higher-fidelity image that would match the original?
It’s amazing that someday we’ll be able to pass in low fidelity pixel art sprite sheets to an AI and get back high definition hand drawn 2D graphics for use in games.
Is there a way to have current AI tools maintain consistency when generating multiple images of a specific creature or object? For example, if there are images of 'Dr. Venom' they need to look similar, or if there are images of the same space ship.
You can force a model to generate nearly the same actual pixels with DreamBooth, which can be interesting for putting people’s faces in a picture, but otherwise I’d call it overfitting.
[flagged]
[flagged]
I seriously have never understood why what gets published in these blog posts isn't just lower res especially since this is precisely about old video game graphics.