Meta AI is introducing a new feature to WhatsApp that allows users to instantly generate images and videos directly within chats. This new tool is part of a broader rollout of Meta AI capabilities across the platform and is now accessible in more than a dozen countries around the world. However, the feature is still in testing phase in India and only selected users will be able to take advantage of the new feature.
Real-time image and video generation
WhatsApp users can bring their imaginations to life in real-time by simply typing in the chat. The AI instantly begins generating images and videos that change with each word you type. This feature uses the latest Llama 3 large language model introduced by Meta.
How to use
The process is simple. When a user types into her WhatsApp chat, a description of a scene, object, or abstract concept, the AI starts visualizing it. The more detail you provide, the more refined the image will be. This allows for a high degree of customization and creativity, ensuring each image generated is unique to the user's input. This differs from current image generation models like his OpenAI's Dall-E 3, which takes a final prompt from the user and creates the image according to the instructions.
User engagement and feedback
Meta claims that it is diligently collecting user feedback to further refine and improve this tool. They encourage everyone to try this feature and share their creations and experiences.
Meta-Rama 3 rollout
Meta also announced the release of Llama 3, its latest large-scale language model that supports real-time image generators powered by WhatsApp. Meta claims this new upgrade provides the best AI available for free.
