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.
2 people where at least one looks like a specific person who was not trained in the original model. As soon as you add something like a Lora into the mix it will try to make everyone like that person.
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.
… have y’all genuinely avoided seeing anything generated since 2022? Even the text-to-whatever models can handle “left guy” versus “right guy.”
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.
2 people where at least one looks like a specific person who was not trained in the original model. As soon as you add something like a Lora into the mix it will try to make everyone like that person.
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.