this post was submitted on 22 Feb 2024
27 points (80.0% liked)

Technology

59148 readers
2338 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
top 4 comments
sorted by: hot top controversial new old
[–] [email protected] 11 points 8 months ago (3 children)

Wtf, they just released stable cascade like a week ago. All they are doing is just confusing the users and model trainers. From the blog post it's not even clear why I would want to use this one over the other one that they just released.

[–] [email protected] 7 points 8 months ago* (last edited 8 months ago)

Cascade is an experiment, SD3 is their mainline model. Also this isn't released, it's just a preview whole they work on SD3.

[–] [email protected] 5 points 8 months ago

to add to the other answers, stable cascade isn't open source :(

[–] [email protected] 2 points 8 months ago

As far as I understand, Stable Cascade is a pretty large architecture change from the existing Stable Diffusion models. Sable Diffusion 3 will likely be an interitive improvement with similar architecture over the existing Stage Diffusion models. The blog post for Stable Cascade does a better job explaining the difference than the Stable Diffusion 3 blog post does. Here's a god quote from that post:

Stable Cascade differs from our Stable Diffusion lineup of models as it is built on a pipeline comprising three distinct models: Stages A, B, and C. This architecture allows for a hierarchical compression of images, achieving remarkable outputs while utilizing a highly compressed latent space.

Hope this helps!