Few Shot Subject Personalization Via Textual Inversion With Class Prior Preservation

via “few-shot subject personalization via textual inversion with class-prior preservation”

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Unique: Implements class-prior preservation through paired regularization loss (subject images + class-prior images) during training, preventing semantic drift and catastrophic forgetting that naive fine-tuning would cause. Uses a unique token identifier (e.g., '[V]') to anchor the learned subject embedding in the text space, enabling compositional generation with novel contexts.

More parameter-efficient and faster than full model fine-tuning (only trains text encoder + UNet layers) while maintaining better semantic diversity than naive LoRA-based approaches due to explicit class-prior regularization preventing mode collapse.