Google has launched its latest and highest quality image generation model yet, known as Imagen 3.
The tech giant announced in a tweet on 10 October that the new model is now available globally through the Gemini App.
Google says that Imagen 3 is better at following instructions, has improved photorealism, and fewer distracting artifacts, making it the best model yet.
Improving Gemini
Gemini is Google’s generative chatbot that was launched in 2023. Initially known as Bard, it was created as a rival to OpenAI’s ChatGPT, which is currently the most popular AI chatbot worldwide.
The first version, Gemini 1.0 started with three models — Ultra, Pro and Nano. At the time, Gemini Ultra was the largest and most capable model for highly complex tasks.
Gemini Pro was the best model for scaling across a wide range of tasks, and Gemini Nano was the most efficient model for on-device tasks.
With the launch of Imagen 3, Google is specifically taking image generation to another level as it is the highest quality model so far. All you have to do is start chatting with the model to start generating high-quality images right away.
The rise of generative AI
Generative AI or Gen AI is AI technology that focuses on creating new and original content. This may be in the form of chat responses, designs, or even deepfakes.
The technology can be used in so many ways, but is majorly used to produce text, images, and to generate artificial data.
Gen AI is notably easy to use, which explains its rapidly increasing popularity among users with different levels of tech familiarity.
Google has contributed immensely to the development of this technology and is now making it better with this new launch, giving it a place as a leader in Gen AI.
ReadNext
