-
Google has updated its Gemini chatbot with the advanced Imagen 3 AI image generator, enhancing visual capabilities for all users.
-
Imagen 3 offers superior photorealism, improved prompt adherence, and fewer unintended elements in generated images, outperforming comparable models.
-
The update includes SynthID technology, embedding invisible watermarks to prevent deepfakes and unauthorized image manipulations.
Google has boosted its Gemini chatbot’s visual capabilities with the integration of its latest image generation model, Imagen 3. This upgrade makes advanced image generation tools available to all users, including those on the free tier, and provides developers with enhanced visual capabilities through the Gemini API.
Imagen 3 boasts impressive features, including superior photorealism, improved adherence to prompts, and reduced unwanted elements. Users can generate images in various artistic styles, from photorealism to textured oil paintings and claymation. Additionally, camera styles can be specified, offering flexibility across different visual aesthetics.
To combat AI-generated content misuse, Google has incorporated SynthID technology, embedding invisible watermarks into generated images. This AI label prevents deepfakes and unauthorized manipulations, ensuring secure and responsible AI use.
With Imagen 3 now available within the Gemini app and API, users and developers can explore Google’s latest AI image generation advancements.
