Meta's Fundamental AI Research (FAIR) team has announced the public release of several new AI models and tools for researchers. These include image-to-text and text-to-music generation models, a multi-token prediction model, and a technique for detecting AI-generated speech. The models are being released under various licenses ranging from research-only to commercial.
Chameleon, which was publicly released, is a family of mixed-modal models that can process and generate text and images. The Chameleon 7 billion and 34 billion models, released under a research-only license, can reportedly handle tasks involving visual and textual understanding, such as image captioning. Another model, JASCO, is designed for text-to-music generation and allows users to control aspects like chords, drums, and melodies through text inputs.
A multi-token prediction model for code completion is also being released under a non-commercial, research-only license. Meta is also releasing AudioSeal, an audio watermarking technique for detecting AI-generated speech within longer audio snippets.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.