wassname/peft
1
0
Fork 0
mirror of https://github.com/wassname/peft.git synced 2026-09-11 12:30:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

minor fixes

Browse Source
This commit is contained in:
Sourab Mangrulkar
2023-01-04 15:16:32 +05:30
parent 4e577cf6e3
commit c8d3def60e
2 changed files with 16 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -67,14 +67,14 @@ Hardware: Single A100 80GB GPU with CPU RAM above 64G
| Model | Full Finetuning | PET-LoRA |
| --------- | ---- | ---- |
| CompVis/stable-diffusion-v1-4 | 66.4GB GPU / 3.97GB CPU / 22 minutes | 15.5GB GPU / 3.84GB CPU / 5.5 minutes |
| CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU / 22 minutes | 15.5GB GPU / 3.84GB CPU / 5.5 minutes |
**Training**
An example of using LoRA for parameter efficient dreambooth training is given in `~examples/lora_dreambooth/train_dreambooth.py`
```bash
export MODEL_NAME="stabilityai/stable-diffusion-2-1" #"CompVis/stable-diffusion-v1-4"
export MODEL_NAME= "CompVis/stable-diffusion-v1-4" #"stabilityai/stable-diffusion-2-1"
export INSTANCE_DIR="path-to-instance-images"
export CLASS_DIR="path-to-class-images"
export OUTPUT_DIR="path-to-save-model"