this post was submitted on 02 Nov 2024
11 points (100.0% liked)

Stable Diffusion

4309 readers
1 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
11
Nerogar/OneTrainer: OneTrainer now supports efficient RAM offloading for training on low end GPUs (github.com)
submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com to c/stable_diffusion@lemmy.dbzer0.com
0 comments fedilink hide all child comments
 

Details: https://github.com/Nerogar/OneTrainer/blob/master/docs/RamOffloading.md

  • Flux LoRA training on 6GB GPUs (at 512px resolution)
  • Flux Fine-Tuning on 16GB GPUs (or even less) +64GB of RAM
  • SD3.5-M Fine-Tuning on 4GB GPUs (at 1024px resolution)
no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here