Nunchaku v0.2.0: Multi-LoRA Support, Faster Inference, and 20-Series GPU Compatibility

github.com

Nunchaku v0.2.0: Multi-LoRA Support, Faster Inference, and 20-Series GPU Compatibility

github.com

Even_Adder@lemmy.dbzer0.com to

Stable Diffusion@lemmy.dbzer0.comEnglish · 15 days ago

GitHub - mit-han-lab/nunchaku: [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

github.com

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models - mit-han-lab/nunchaku

Announcement: https://github.com/mit-han-lab/nunchaku/discussions/236

You must log in or register to comment.

Chat

Stable Diffusion@lemmy.dbzer0.com

stable_diffusion@lemmy.dbzer0.com

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !stable_diffusion@lemmy.dbzer0.com

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

45 users / day
82 users / week
90 users / month
198 users / 6 months
1 local subscriber
4.6K subscribers
86 Posts
43 Comments
Modlog

mods:
db0@lemmy.dbzer0.com