Google’s Imagen Editor now lets you submit an image, choose a region that you want edited/altered, and then issue a text prompt for that specific area. The rest of the picture is not touched, at a high level.
Soon after the changes arrive in Imagen Editor, 9to5google added, Google released other assorted examples and an accompanying research paper. Though, not releasing Imagen Editor to the public, maybe, due to concerns in relation to responsible AI.
Additionally, shows an example highlighting the body of a dog and then asking for a red spacesuit with a white star. On the right, the demo adds a rocket made out of cardboard, while the most impressive is adding blue gaming headphones.
They introduced a method that gauges the quality of image editing models. In addition to that, while recreating visuals would be time-consuming or infeasible (e.g., tweaking objects in vacation photos or perfecting fine-grained details on a cute pup generated from scratch) TGIE allows quick, automated, and controllable editing as a convenient solution. This comes as Google Photos is getting a Magic Editor feature that leverages elements of generative AI.
…text-guided image editing (TGIE) is a practical task that involves editing generated and photographed visuals rather than completely redoing them.
Imagen and other Google text-to-image model testing in Workspace Labs have recently begun. While image generation for custom Google Meet backgrounds has also been announced. They should first become available to users in Google Slides.