MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation

no code implementations • 17 Apr 2024 • Kuan-Chieh, Wang, Daniil Ostashev, Yuwei Fang, Sergey Tulyakov, Kfir Aberman

MoA is designed to retain the original model's prior by fixing its attention layers in the prior branch, while minimally intervening in the generation process with the personalized branch that learns to embed subjects in the layout and context generated by the prior branch.

Disentanglement Image Generation

Personalized Restoration via Dual-Pivot Tuning

no code implementations • 28 Dec 2023 • Pradyumna Chari, Sizhuo Ma, Daniil Ostashev, Achuta Kadambi, Gurunandan Krishnan, Jian Wang, Kfir Aberman

This approach ensures that personalization does not interfere with the restoration process, resulting in a natural appearance with high fidelity to the person's identity and the attributes of the degraded image.

Image Restoration