A Coming-Out Party for Generative A.I., Silicon Valley’s New Craze
nytimes.comIf you're reading this and you haven't played with Stable Diffusion yet, try any of the following quick-and-easy generators:
https://stablediffusionweb.com
Not sure what to type? Copy and paste prompts from any of the following prompt databases:
Want to run it on your own computer? Install any of the following:
I’ve been having a lot of fun using Midjourney to create images based on lyrics for music videos (here’s one for Kashmir by Led Zeppelin https://www.youtube.com/watch?v=un0XZMubeCE).
I can’t speak for anyone else, but this is probably the most magic I’ve felt from a new piece of technology. Each time I generate a new images, it’s a surprise. I can usually identify something in the image based on the prompt, but sometimes it’s wild and completely out of left field. I’ve probably generated a few thousand images so far and don’t see myself stopping anytime soon.
One change I’d like to see is in language allowed. I don’t get why Midjourney allows “kill” and “die” but not “bloody”.
I hope you will run your own locally instead of letting Midjourney block and/or mess with your prompts.
That is so cool. If those images could morph into each other, you'd have generative music videos.