As far as I can see, they're just typing a prompt into Stable Diffusion or DALL-E and picking a nice image.
It's lazy, talentless, and demeans the actual artists whose work was stolen to train these models.
As far as I can see, they're just typing a prompt into Stable Diffusion or DALL-E and picking a nice image.
It's lazy, talentless, and demeans the actual artists whose work was stolen to train these models.