American tech giant Google has recently released the Imagen 3 image generator to the public. Previously, it was only available to select Vertex AI subscribers, but the tool is now free to use for all users in the US. This new tool is reported to bring “Google’s state of the art image generative AI capabilities to application developers.”
In a research paper accompanying the release, Google states, “We introduce Imagen 3, a latent diffusion model that generates high-quality images from text prompts.”. The paper details the quality and safety concerns regarding the product and describes various user experiences.
Currently, the response to the new AI has been mixed. Some users are highlighting its improved texture and better attention to detail. Others have criticized the strict content policy as it limits creativity.
See Related: OpenAI Reveals “Sora”: A Text-to-Video AI Model Set to Change The Generative AI Landscape.
The expansion of Imagen 3’s availability coincides with the release of Grok-2, another AI model developed by X. Notably, Grok-2 has much more relaxed filters, which has led to many comparisons.
The Imagen 3 was originally announced during the Google I/O event in May. Like other similar AI models, Imagen 3 generates images from text prompts. To stand out from the competition, Google promised that its new tool is “capable of generating images with even better detail, richer lighting, and fewer distracting artifacts” compared to previous models.
Users can try out Imagen 3 via the ImageFX platform.
