You can now generate images on Gemini using the Imagen 3 AI model
Google on Wednesday announced a significant upgrade to Gemini, its internal artificial intelligence (AI) model. The company announced that the chatbot’s image generation capability will now be handled by the Imagen 3 AI model for all users. Imagen 3 is the latest and most capable image generation model from the Mountain View-based tech giant. In addition to the Gemini app, the feature is also being extended to the API version of Gemini, allowing developers to build apps and experiences based on this capability.
Gemini users get access to the Imagen 3 AI model
In one after on degree of photorealism, better fast compliance and adds fewer unwanted elements to images.
Gadgets 360 employees were able to verify that the Gemini app does indeed use Imagen 3 to generate images. To test its capabilities and compare it to Meta AI, we gave both chatbots the same prompt. The assignment was: ‘Draw a picture of a golden retriever dog sitting on a train berth and looking through the window at the Alps. The train has a wooden interior and the seats are green in color. All the other passengers on the train are animals too. One human conductor checks for tickets.”
The generated images can be seen above. While both AI models failed to include one or more elements indicated in the prompt, Gemini was able to include more elements. While Meta AI generates images in 1280 x 1280 resolution, Imagen 3 images are generated in 2048 x 2048 resolution.
Imagen 3 can generate images in a wide range of styles, such as photorealistic, textured oil paintings and claymation scenes. Users can also request that images appear as if they were taken with a specific camera, such as a Nikon DSLR, GoPro style, wide-angle lens and more.
Google has said that its AI model comes with built-in safeguards to reduce the risk of deepfakes. Each generated image is also watermarked with SynthID, a technology that adds an invisible AI label within the pixels of the image. It cannot be cropped or deleted and is even present in screenshots.