2026
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
ICLR 2026poster
Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model’s original generative capabilities. However, this process often leads to overfitting, where the model ignores the user’s prompt and merely replicates…