After $10Billion ChatGPT deal, now Microsoft Research recently launched new module called “Visual ChatGPT” which allows users to send their image requests via chat and receive it with editing functionality. Still we have to wait and see how smart comparing to Dall-E2. In official statement MS research says Visual ChatGPT uses different visual foundation models to let users to get the best output images.
What Visual ChatGPT will do?
It’s very simple, If you upload an Matt black photoframe and request ChatGPT to change the colour as Deep purple and add moon object inside the frame then V-ChatGPT will do the work for you. It doesn’t stop here you can also prompt to convert an normal image into cartoon format. Stil lot of enhancements are on the works but we have to wait and see how users are going adopt this technology on their daily use.
Still the Visual ChatGPT yet to be available for all, but here is the GitHub respiratory to find more details – Visual ChatGPT
