If we already have AI software, like Stable Diffusion and Midjourney, that can generate one brand new image based on a text prompt, couldn’t it generate 24 of them?

Couldn’t the AI image generation model eventually be trained to render entire videos with a text prompt, and couldn’t that algorithm eventually be trained to generate sounds and dialog as well?

Wouldn’t this eventually become a paid streaming service where you put in a prompt, and a full-fledged movie pops out the other end? A movie that required no writers, directors, actors, sets, costume designers, or editors to create, just some AI software.

[Read More…]