yuvalkirstain/PickScore_v1 is an open-source model designed to score and rank images based on their alignment with text descriptions. It is commonly used in image generation pipelines to select the best outputs from models like Stable Diffusion. The model is available on Hugging Face and can be integrated into local or cloud-based AI workflows for automated image evaluation.
In the Other AI space, PickScore takes a focused approach. Automatically evaluating and ranking generated images according to how well they match a given text prompt. PickScore is an open-source project aimed at AI developers and researchers. PickScore is open source under the MIT license. It ships for the web and API.
Yuval Kirstain builds and maintains PickScore, and it first shipped in 2023. Development happens publicly on GitHub with 600 stars. Key capabilities include Image Scoring, Preference Prediction, and Text-Image Alignment.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match