Imagen 3, Google’s new AI image generator, is now available to everyone through Gemini, including free accounts. And it produces simply stunning results!
After a suspension linked to controversies over the use of generated content, Gemini has once again been able to generate images from simple textual descriptions – called prompts – since last August. Abstract painting, manga drawing, realistic photo, pencil portrait… Nothing is impossible! For this, it can count on the Imagen 3 model. Unveiled in May during Google I/O 2024, this new version adds several major aspects to image generation.
And if it has been several months now that users in France have been able to access the image generator without needing to go through a VPN, access to Imagen 3 was only possible for professionals or through paid services. Since October 9, Google has extended access to this technology to everyone, including free users.
Imagen 3 Gemini: a more powerful model for hyper-realistic results
The new version of Imagen improves several aspects of the image generator. In fact, it increases the overall quality of images, while adding numerous details which make an image much more photorealistic. It also allows you to use different styles to modernize the result obtained. Enough to make up for part of the delay compared to Midjourney, which is today the only generative AI capable of producing images truly indistinguishable from reality – which is also particularly problematic for the dissemination of fake news…
Image generation with Imagen 3 is now available to all Gemini users around the world.
Imagen 3 is our highest quality image generation model yet and brings an even higher degree of photorealism, better instruction following, and fewer distracting artifacts than ever before. pic.twitter.com/E8CrcyFcz5
— Google Gemini App (@GeminiApp) October 9, 2024
It is very simple to use Imagen 3, since there is no special manipulation to do. Simply launch Gemini, then ask the artificial intelligence to generate an image via a prompt, giving it as many details and indications as possible, in particular the rendering style. The chatbot will then take care of generating an image and, if it is not suitable or if it requires some small modifications, all you have to do is submit a new request to Gemini, adjusting the prompt.
For simplicity, Google already plans to allow users to modify specific parts of an image to improve personalization. Although this option is still in the testing phase, it should be deployed soon.
Please note that it is only possible to generate people with a Gemini Advanced, Business or Enterprise account. In addition, since its relaunch in August, Imagen 3 has complied with stricter rules regarding the generation of sensitive content, in order to prevent abuse such as the creation of deepfakes or disinformation.