MGM Collection Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated May 3 • 46
From screenshots to HTML Collection WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot. • 4 items • Updated Apr 15 • 18
Lumiere: A Space-Time Diffusion Model for Video Generation Paper • 2401.12945 • Published Jan 23 • 86