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

A synthetic dataset of over 65,000 identities, each associated with multiple images of that person.

Data and Resources

Cite this as

Kuan-Chieh Wang, Daniil Ostashev, Yuwei Fang, Sergey Tulyakov, Kfir Aberman (2024). Dataset: MOA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation. https://doi.org/10.57702/8fiklulm

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Kuan-Chieh Wang
More Authors
Daniil Ostashev
Yuwei Fang
Sergey Tulyakov
Kfir Aberman