Salesforce has launched a new model called BLIP which can caption images, visual question-answering, and image-text matching.
To learn more, please read the LinkedIn post by Younes Belkada. You can also read the original paper here, or play with the model yourself by clicking here.
Member of the Swiss Association for Standardization
© 2023 AI Transparency Institute – All rights reserved | Website crafted with love by agencecopilote
Username or Email Address
Lost your password?