Stable Diffusion

4290 readers

30 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago

MODERATORS

[email protected]

Canny and Inpainting ControlNets for Würstchen v3 Have Been Trained (i.imgur.com)

submitted 8 months ago by [email protected] to c/[email protected]

4 comments fedilink hide all child comments

https://nitter.net/dome_271/status/1749494484897796355 dome | Outlier @dome_271 Jan 22

We trained some ControlNets for Würstchen v3. You can try them out on the discord: discord.gg/Me98gUvRH9

There are canny and inpainting atm

"photo of an alien from Area 51"

all 5 comments

sorted by: hot top controversial new old

[–] [email protected] 6 points 8 months ago

They took the precious, they did!

[–] [email protected] 1 points 8 months ago (1 children)

so, what's Würstchen?

[–] [email protected] 1 points 8 months ago (1 children)

It's a much cheaper to train Text to Image model.

[–] [email protected] 1 points 8 months ago

Here is an alternative Piped link(s):

cheaper to train Text to Image model

Piped is a privacy-respecting open-source alternative frontend to YouTube.

I'm open-source; check me out at GitHub.