Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?
This is your opportunity to ask questions. No question too simple or too silly.
Culture war topics are accepted, and proposals for a better intro post are appreciated.
Jump in the discussion.
No email address required.
Notes -
Is there video upscale software which learns from its input? E.g. there a footage where interveaned close up face shots and group shots, the upscaler might learn from face shots to improve group shots. For single images there are fractal upscalers which I think can do that, but for videos? (I guess it is possible to feed composed frames to single-image upscaler, but probably not worth in practice).
Not that I'm aware of. There are things like "Topaz Video AI" that does AI enhancement and are trained on a large dataset. They work well enough that trying to add to the training on a small dataset isn't seen as worth the effort.
Being trained on barely related large dataset can be bad; e.g. most neural networks cannot draw realistic image of Van Gogh or Venus of Milo because large number of samples images in Van Gogh style and pictures of people with arms LoRA does wonders.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link