News for hackers. Stuff that matters.

A comment on SDXL Turbo: A Real-Time Text-to-Image Generation Model. Parent comment

Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by torginus on Wednesday November 29, 2023 @02:38AM (#38456627)
Isn't literally every imagegen AI that's not DALL-E or Midjourney based on Stable Diffusion?
[ Parent | on HN ]
Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by cubefox on Wednesday November 29, 2023 @03:56AM (#38457121)
There are exceptions, e.g. https://generated.photos/human-generator uses a GAN based model.
[ Parent | on HN ]
Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by hospitalJail on Wednesday November 29, 2023 @04:55AM (#38457501)
Are we sure that those arent based on stable diffusion?

No code black box, and we get to tease the closed source companies for wrapping FOSS stuff.

Midjourny I'm most convinced is just a SD with a fine-tuned model. That would explain why everything looks like pixar and can't follow the prompt.

[ Parent | on HN ]
Re:SDXL Turbo: A Real-Time Text-to-Image Generation Model by fragmede on Wednesday November 29, 2023 @01:18PM (#38462994)
Given that Midjourney predates StableDiffusion, that seems unlikely, though it is possible they threw away all their hard work to create their model to use one that's available to other people for free and then charge money for it.
[ Parent | on HN ]