DeepFloyd IF is a crazy good text-to-image model - and open source

The DeepFloyd team, affiliated with StabilityAI, has replicated this architecture and released a kind of open-source image called IF. According to the team, IF demonstrates the high image quality and language understanding capabilities of Imagen. It was trained with around 1.2 Billion images from the LAION-5B dataset.

read more

Previous
Previous

EU Urged To Protect Grassroots AI Research Or Risk Losing Out To US

Next
Next

Stability AI Develops Stable LM, A New Open Source Language Model