News for hackers. Stuff that matters.
Re:Imagen, a text-to-image diffusion model by refulgentis on Monday May 23, 2022 @05:23PM (#31484922)
You think so? I'm very high on the Kool-Aid, image generation and text transformation models are core parts of my workflow. (Midjourney, GPT-3)

It's still an unruly 7 year old at best. Results need to be verified. Prompt engineering and a sense of creativity are core competencies.

Re:Imagen, a text-to-image diffusion model by visarga on Monday May 23, 2022 @05:39PM (#31485107)
> Prompt engineering and a sense of creativity are core competencies.

It's funny that people are also prompting each other. Parents, friends, teachers, doctors, priests, politicians, managers and marketers are all prompting (advising) us to trigger desired behaviour. Powerful stuff - having a large model and knowing how to prompt it.