[ad_1]
Google announced Imagen 3, the latest version of its image generation model, on its I/O event for developers in Tuesday.
Imagen 3 produces more photorealistic images, including details such as sunlight or animal whiskers. I also remember incorporating smaller details like wildflowers or birds into longer prompts.
More from Google I/O 2024
Throughout 2024 so far, we’ve seen a flurry of image and video generation models from the likes of OpenAI, Adobe and Google themselves as they seek to extend chatbots far and wide beyond the text and win over users.
According to Douglas Eck, senior research director at Google, Imagen 3 is Google’s best model yet for rendering text, which is a challenge for image generation models.
“It understands prompts written the way people write,” he said. “The more creative and detailed you are, the better.”
The latest version also generates less distorted images.
Next up release of Imagen 2 in December 2023
Registrations for access to Imagen 3 are open today and will soon be available to developers and enterprise customers at Vertex AI.
This is a developing story.
Editor’s note: CNET used an AI engine to help create a handful of stories. Reviews of AI products like this, just like Other CNET hands-on reviews, are written by our human team of in-house experts. For more see CNET’s AI policy and how we test AI.
[ad_2]
