Google announced the latest version of its image-generating AI model, Imagen 3, at the I/O 2024 developer conference. The new model is developed to interpret and translate text prompts into images more effectively.
Some of Imagen 3's main features include an enhanced understanding of text prompts, more creative and detailed image generation, and a reduction in distracting artifacts and errors. It also excels in rendering text, a traditionally challenging area for image-generation models, and integrates SynthID, an invisible watermarking approach for security.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.