Stable Diffusion XL Turbo can generate AI images as fast as you can type (arstechnica.com)

submitted 11 months ago by Blaze@discuss.tchncs.de to c/stable_diffusion@lemmy.dbzer0.com

13 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] MagicShel@programming.dev 12 points 11 months ago

It is indeed amazingly fast. I actually hate the constant generation of pictures while I'm typing - particularly given that I used up my free usages with two prompts.

The quality of people is poor, trending toward disfigurement. It does landscapes well.

[-] Rodeo@lemmy.ca 12 points 11 months ago

The article says they ran it locally with Automatic1111. No need to be hampered by some website's rate limiting.

[-] MagicShel@programming.dev 3 points 11 months ago

That would certainly be better. My local computer is suffering some Linux issues after a permanent move from windows, and I haven't set back up any local AI stuff until I sort it.

[-] dream_weasel@sh.itjust.works 4 points 11 months ago

Sounds like your PC is just recovering from a case of windows ;).

[-] Blaze@discuss.tchncs.de 2 points 11 months ago

Same here

[-] scrubbles@poptalk.scrubbles.tech 2 points 11 months ago* (last edited 11 months ago)

How do we try it? Edit nvm it's right in the article

this post was submitted on 30 Nov 2023

21 points (92.0% liked)

Stable Diffusion

4310 readers

5 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago

MODERATORS

db0@lemmy.dbzer0.com