diffusers
a98a839d
- Reduce Memory Cost in Flux Training (#9829)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Hide Comment Changes
Previous Change (CTRL+↑)
Next Change (CTRL+↓)
Expand Context Lines
Collapse Context Lines
Hide Minimap (CTRL+M)
Commit
252 days ago
Reduce Memory Cost in Flux Training (#9829) * Improve NPU performance * Improve NPU performance * Improve NPU performance * Improve NPU performance * [bugfix] bugfix for npu free memory * [bugfix] bugfix for npu free memory * [bugfix] bugfix for npu free memory * Reduce memory cost for flux training process --------- Co-authored-by: 蒋硕 <jiangshuo9@h-partners.com> Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
References
#9829 - Reduce Memory Cost in Flux Training
Author
leisuzz
Parents
3deed729
Files
2
examples/dreambooth
train_dreambooth_flux.py
train_dreambooth_lora_flux.py
Loading