Using the diffusers library and combining multiple optimizations
- Gradient checkpointing
- Mixed precision training
- 8-bit Adam
- Gradient accumulation
This allows using LoRA to fine-tune SDXL with DreamBooth on a T4 GPU, which is provided by free in Google Colab.
1 comment
[ 3.0 ms ] story [ 15.2 ms ] threadThis allows using LoRA to fine-tune SDXL with DreamBooth on a T4 GPU, which is provided by free in Google Colab.