Google has unveiled a new artificial intelligence model called “Imagen”, capable of creating an image from a simple text description.
Google has announced a new AI tool that can generate graphics from text input. Any descriptive language can be entered into the programme, and it will build an image as exactly as realistic.
This isn’t the first time an AI model for image creation has gained traction. DALL-E from OpenAI could also generate graphics from text, but Google’s version is more accurate.
Google’s programme is called Imagen, and it was developed by Google Research’s Brain Team. The search engine powerhouse promises to be able to provide “new levels of visual art and language understanding” with the AI tool.
Read more: Google offers $100,000 worth of free online tech courses to every U.S. company
Google established the Drawbench standard to evaluate Imagen to other text-to-image models. This benchmark has a set of 200 text prompts that were entered into several AI systems for image creation. Human raters were then shown these photos. “In side-by-side comparisons, both in terms of sample quality and image-text alignment, Google prefers Imagen over other models,” Google notes.
However, it’s worth noting that the photographs on Imagen’s website have been chosen and may represent the tool’s best work. The model’s visuals will not always be precise.
Imagen, like other text-to-AI solutions, is not yet accessible to the general public. Google believes it is currently unsuitable for the general public and requires further refinement. In the future, the team may make it available to the public, although access will most certainly be limited.
On Imagen’s website, you can try a limited version of the game right now. Only pre-selected sentences can be used to generate a description.