DayFR Euro

New from Adobe Stock: Edit your images with AI before using them

Adobe Stock, one of the largest image and photography banks, benefits from new artificial intelligence tools. Adobe’s Firefly AI model powers two new features: Generative Edits and Generative Variations. Generative edits allow you to use AI to modify existing stock images. Generative variations also use photos from the Adobe database as reference guides to create new images.

Generative edits will include the ability to remove the background of an image and replace it with AI-generated elements. You can also enlarge an image. These tools use the Stock image to create a consistent rendering between the original elements and those generated by the AI.

Adobe Stock contributors will be compensated if their images are used

Generative variations create entirely new images, using the base image as a style or composition reference. So if you like the layout of an image, like the location of elements, depth, clarity, etc., you can tell Firefly to refer to that design when it generates what you ask it to do. You can do the same thing with styling, directing the AI ​​towards a particular color palette or aesthetic.

Photographers who submit their works to Adobe Stock already agree to have the company train its AI models on their creations. They cannot refuse to have these new AI tools used on their works. Contributors to Stock will be compensated when their work is used to generate alternative versions and those AI versions are uploaded.

Adobe has invested heavily in AI. Its photo and video editing programs have recently been given a series of new AI-powered editing tools, and soon Adobe users will be able to generate videos in addition to images thanks to its Firefly model. The company is also investing in enhancing AI labels with content certificates and the Content Authenticity initiative.

Libraries like Adobe’s have become even more important in the AI ​​era as tech companies look for content sources on which to train their models. Adobe AI models are only trained on Adobe Stock and other public domain content (such as content with expired copyrights), not on content from individual creators or content taken from the open web.

-

Related News :