Add to Favourites
To login click here
Microsoft Research has recently published a paper that introduces a new architecture, Visual ChatGPT, which bridges the gap between text-to-image and natural language generation. This new architecture combines the strengths of an LLM like ChatGPT with the power of image generation, allowing for more organic interactions with AI. The demo adds capabilities of sharing images with ChatGPT, facilitated through a system architecture that utilises a ‘prompt manager’ to share information between various visual foundation models.
