WhatsApp is apparently working on a up-to-date generative AI feature that should let users create personalized avatars to exploit in any imaginable setting. The feature is in development, spotted in the up-to-date WhatsApp beta for Android 2.24.14.7 by WABetaInfowill likely exploit a combination of user-supplied images, text suggestions, and Meta’s AI Llama model to generate images.
Screenshot provided by WABetaInfo says that users can imagine themselves “in any environment, from a forest to outer space.” The examples look pretty typical of those generated by AI generators, especially if you’ve used apps like AI lens or Snapchat’s “Dreams” selfie feature.
To create a personalized avatar, WhatsApp users will need to “take photos of themselves once,” which will then be used to train Meta AI to create images in the user’s likeness in any environment. WhatsApp users will then be able to generate their avatars by typing “Imagine me” with a description of the environment in a Meta AI chat, or in other WhatsApp conversations by typing “@Meta AI imagine me…”
This feature will reportedly be optional and users will have to manually enable it in WhatsApp settings before using it. WABetaInfo also informs that reference images can be removed at any time via the Meta AI settings.
