Dreambooth-Stable-Diffusion and stable-dreambooth
These are competitors offering alternative implementations of the same Dreambooth fine-tuning technique for Stable Diffusion, with the first providing a more feature-rich reference implementation while the second prioritizes code simplicity and accessibility.
About Dreambooth-Stable-Diffusion
XavierXiao/Dreambooth-Stable-Diffusion
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
Fine-tunes the entire diffusion model's U-Net weights (rather than just embeddings) using paired subject images and class-level regularization images to prevent overfitting. Leverages gradient checkpointing and the Stable Diffusion v1 architecture, requiring a rare token identifier and synthetic or real regularization images during training to maintain model generalization across semantic variations.
About stable-dreambooth
Victarry/stable-dreambooth
Dreambooth implementation based on Stable Diffusion with minimal code.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work