tomg-group-umd/pixelprose download history

tomg-group-umd/pixelprose is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,219 times (204 in the last 7 days), and 19,204 times in total. It ranks #16,657 among datasets by monthly downloads.

From Pixels to Prose: A Large Dataset of Dense Image Captions [ arXiv paper ] | [ 🌮 image tars ] PixelProse is a comprehensive dataset of over 16M (million) synthetically generated captions, leveraging cutting-edge vision-language models (Gemini 1.0 Pro Vision) for detailed and accurate

Models trained on pixelprose

6 models list it as training data.

Open tomg-group-umd/pixelprose on Hugging Face