News for hackers. Stuff that matters.

A comment on Running Stable Diffusion XL 1.0 in 298MB of RAM. Parent comment

Re:Running Stable Diffusion XL 1.0 in 298MB of RAM by Cannabat on Wednesday October 04, 2023 @07:48AM (#37763801)
Fooocus does quite a bit of prompt massaging for you - there are models that take a few words and turn them into “prompt engineer” level prompts. Makes a huge difference.
[ Parent | on HN ]
Re:Running Stable Diffusion XL 1.0 in 298MB of RAM by brucethemoose2 on Wednesday October 04, 2023 @12:01PM (#37767124)
Yeah, and InvokeAI has a similar "IP-adapter" model.

Still, even with it turned off, the quality is quite remarkable.

[ Parent | on HN ]
Re:Running Stable Diffusion XL 1.0 in 298MB of RAM by Cannabat on Wednesday October 04, 2023 @03:45PM (#37770583)
Ip adapter is a bit different from what fooocus and midjourney do.

Ip adapter uses an image to guide denoising.

Fooocus and MJ take a prompt and expand it in a variety of ways (eg a language model or more simplistic text manipulation). The actual prompt that creates the conditioning is not what you typed in. That’s what I mean by prompt massaging

[ Parent | on HN ]