DreamBooth

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation https://arxiv.org/abs/2208.12242

- > [@psuraj28](https://twitter.com/psuraj28/status/1575123562435956740?s=21&t=nsEudpoT1W4dsOjQVkyQyg): dreambooth #stablediffusion training is now available in 🧨diffusers!
- > And guess what! You can run this on a 16GB colab in less than 15 mins!
- > ![image](https://pbs.twimg.com/media/Fdv2h9TWYAAun3H.jpg)
- VRAM16GB、15分でファインチューニングできる
- Textual Inversionと原理が違って顔のデザインが維持されてる？