You're currently viewing an old version of this dataset. To see the current version, click here.

RECAP: Principled Recaptioning Improves Image Generation

A text-to-image diffusion model trained on a recaptioned dataset to improve image generation quality and semantic alignment.

Data and Resources

Cite this as

Eyal Segalis, Dani Valevski, Danny Lumen, Yossi Matias, Yaniv Leviathan (2024). Dataset: RECAP: Principled Recaptioning Improves Image Generation. https://doi.org/10.57702/8df5ubns

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2310.16656
Author Eyal Segalis
More Authors
Dani Valevski
Danny Lumen
Yossi Matias
Yaniv Leviathan
Homepage https://arxiv.org/abs/2303.12345