Personalize a diffusion model with DreamBooth LoRA
An official Diffusers workflow for training a small image-generation adapter from photos of a specific subject.
Published by Hugging Face Diffusers
How to use it
The publisher uses a small dog-photo example and shows how to run train_dreambooth_lora.py with Accelerate. The example adapts a diffusion checkpoint to reproduce a subject using an instance prompt.
Use images you have the right to train on. Compare generated samples for prompts seen during training and new contexts to check whether the adapter preserves the subject while varying pose and background.
- Framework
- Hugging Face Diffusers
- Dataset
- diffusers/dog-example
- Hardware
- Publisher documents memory-saving settings. Minimum VRAM for the LoRA example is unspecified.
- Access
- Public publisher script and examples; checkpoint and image rights apply.