• 109 Posts
  • 8.87K Comments
Joined 2 years ago
cake
Cake day: August 27th, 2023

help-circle







  • Fuck software patents.

    Copyright made sense when it was a decade or two. Industrial patents seem basically functional. Trademark’s mostly truth-in-advertising for consumer choice.

    But software patents aren’t about how you do something - they’re claiming the entire concept, in the broadest possible terms, and killing it. Straight-up murdering that potential. It is denied the necessary iterative competition that turns dogshit first implementations into must-have features. Nobody’s gonna care in twenty years.

    Entire hardware form-factors have come and gone in a single decade. Can you imagine if swipe keyboards were still single-vendor, and still worked like in 2009? Or maybe Apple bought them, and endlessly bragged about how Android can’t do [blank], because fifty thousand dollars changed hands in the 3G era.

    How many games would not exist, if Nintendo had decided they own sidescrollers? A whole genre, wiped out, because a piece of paper says those mechanics are theft.





  • So if I searched “AI-generated” and “crossover” on a Rule 34 site, it’s just Superman and Marge Simpson. Right? Only the super popular characters that any model can pull off out-of-the-box. Due to totally insurmountable obstacles, there’s no way I’m gonna find Loona from Helluva Boss doing the weird stuff with Sans Undertale.

    … huh, that combo doesn’t actually exist. Shame, it sounded hilarious. There’s one of Loona and Toriel, though, with… Katia fucking Managan? Yeah come on, if some quest-thread webcomic character can show up at an orgy that’s not just herself, I think we can say loras work fine for two people.



  • Text to anything is the least version. You can perform a line yourself, out loud, with your human mouth, and then the model will make that sound like the voice you want.

    Diffusion turns whatever you have into whatever you describe. It’s powerful enough to work on noise. If you want even that to be consistent, just use the same noise, with a fixed seed. Otherwise - put in literally any more effort than asking nicely.

    So you can’t have 2 people in the video.

    … have y’all genuinely avoided seeing anything generated since 2022? Even the text-to-whatever models can handle “left guy” versus “right guy.”

    At this stage, it’s literally easier to learn real film editing than it is to prompt engineer 1 minute of continuous footage.

    A clip I saw ages ago showed a guy walking through his backyard holding a cardboard tube like a rifle, and then the result of presumably typing ‘monkey soldier walking through rainforest’ was Wish.com Planet Of The Apes. But: same camera motions, same body language. This tech is CGI for dummies. You don’t have to engineer shit, when you can nail down the animatic with amateurs. Or dolls.

    You could apply this shot-by-shot to Who Killed Captain Alex, and it would look better than any Steven Seagal movie.