Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image

A new benchmark for evaluating text-to-image generation models, constructed to analyze semantic issues in text-based image generation.

Data and Resources

Cite this as

Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, Daniel Cohen-Or (2024). Dataset: Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image. https://doi.org/10.57702/7gazgk9h

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2301.13826
Author Hila Chefer
More Authors
Yuval Alaluf
Yael Vinker
Lior Wolf
Daniel Cohen-Or
Homepage https://AttendAndExcite.github.io/Attend-and-Excite/