WhatsApp appears to be working on a new generative AI feature that will allow users to create personalized avatars to use in any environment they can imagine. Spotted by WABetaInfo in the new WhatsApp Beta for Android 2.24. 14.7, the in-development feature will apparently use a combination of user-provided images, text prompts, and Meta’s AI Llama model to generate the images.
A screenshot shared by WABetaInfo says that users can imagine themselves in “any environment from the jungle to outer space.” The examples will sound familiar, especially to those who use apps like Lensa AI or Snapchat’s “Dreams” selfie feature.
To create a personalized avatar, WhatsApp users will need to “take a single photo of themselves.” This will then be used to train Meta AI to produce images in the user’s likeness in any environment. Users of the app will then be able to create their avatars by typing “Imagine me” in the setting’s description in a Meta AI chat, or by typing “@Meta AI imagine me…” in other conversations.
The feature will reportedly be optional and will require users to manually enable it in WhatsApp’s settings before it can be used. WABetaInfo also notes that reference images can be deleted at any time via the Meta AI settings.
When will WhatsApp open its new feature to all its users?
There’s no indication of when the new Imagine AI selfie feature will be made generally available. WhatsApp is still rolling out support for its Meta AI chatbot, as well as more general real-time AI image generation for users in the US. So it could be a while before the new AI avatar feature launches. It wouldn’t be a surprise if Meta takes a more cautious approach, given the issues seen with previous generative AI tools.