1.3k citations · 3.7k across the 43 of their papers we have counts for
3 papers · 1 filter
Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
Yuval Kirstain, Adam Polyak, Uriel Singer +3
The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address th…
Vision Transformers with Mixed-Resolution Tokenization
Tomer Ronen, Omer Levy, Avram Golbert
Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natura…
X&Fuse: Fusing Visual Information in Text-to-Image Generation
Yuval Kirstain, Omer Levy, Adam Polyak
We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-i…