Stable Diffusion

IFML research collaborations power next generation of multimodal AI with OpenCLIP and DataComp

•OpenCLIP, the main text/image encoder in Stable Diffusion, is in the top 1% of all Python packages and has more than 50,000 git clones per day. •DataComp is the first rigorous benchmark for advancing multimodal dataset creation. DataComp-1B now outperforms OpenAI’s CLIP on Imagenet.

Read More