Imagen from Google can use text to create images, paintings, CGI renders using AI – here are some images
Imagena AI image generator.
- Images is a text-to-image generator that uses a given description to generate images.
- Images can create drawings, CGI renders, oil paintings and more.
Search giant Google has announced Imagen, an AI-based text-to-image generator, which the company claims has “an unprecedented degree of photorealism.” The AI image generator creates accurate images based on the provided description.
Imagen from Google is similar to the DALL-E 2 AI image generator, however, it is supposed to generate more detailed and accurate images. The generator can draw, paint, create oil paintings, or even develop CGI renders, whatever you want it to do.
For example, if you enter “teddy bear swimming at the olympics”, Imagen will generate the image below –
The image below is generated when you type the text “a dragon fruit wearing a karate belt in the snow”.
The image generator uses scattering technologies that use a pure noise image and then slowly refine it until the AI can no longer improve it. Google has also used large language models that enhance language understanding and compelling language models.
Imagen starts by taking the description and then generates a 64 x 64 pixel image. After two enhancements, the image is converted to a larger 1024 x 1024 pixel image. The AI creates new resolutions with the smaller image.
You can find some of the images generated by Imagen here.
Note that these are the images that Google has selected to feature here. It is possible that not all images are equally good and that the company has selected the best images.
Google claimed that Imagen consistently generates better images than DALLE-2, based on its DrawBench benchmark.
Elon Musk says he doesn’t use flight attendants in apparent denial of sexual harassment allegations against him
California bill could allow parents to sue social media companies for up to $25,000 if their children become addicted to the platforms
Google’s new digital wellbeing research needs your data to dig deeper into user behavior and reduce the risk of smartphone addiction