Adobe releases new Firefly-powered generative AI feature for Photoshop Beta

    Adobe has released a new beta feature for Photoshop that uses generative AI to help users create more realistic and creative images.

    The new feature, called Generative Fill, allows users to simply type a text prompt into Photoshop and the software will automatically fill in the selected area of the image with new content that matches the prompt. For example, you could type “a beach scene with palm trees” and Photoshop would generate a new image of a beach with palm trees.

    Generative Fill is powered by Adobe’s Firefly AI platform, which uses machine learning to generate realistic images from text descriptions. The technology is still under development, but it has already been used to create some impressive results. In addition to filling in selected areas of images, Generative Fill can also be used to remove objects from images, add new objects to images, and even change the style of an image.

    Adobe is currently offering the Generative Fill feature as a beta to Photoshop subscribers. The feature is available in the desktop version of Photoshop and it can be accessed by clicking on the “Generate” button in the toolbar.

    To use the feature, simply select an area of the image that you want to fill in and then type a text prompt into the text box. Photoshop will then generate a new image with the text prompt filled in.

    The feature is definitely still under development, but after some trial and error, I was able to get it to generate so some impressive results. In one image, I was able to get it to generate a flock of birds in the sky, while another I gave it a photo of a blank street and asked it to create a car, which it did a reasonable job at, not perfect, but also not bad.

    Here are some examples of what you can do with Generative Fill:

    • Fill in missing parts of an image: If your image is missing a sky, you can use Generative Fill to add a new sky.
    • Remove objects from an image: If you want to remove an object from an image, you can use Generative Fill to fill in the space where the object was.
    • Add new objects to an image: If you want to add a new object to an image, you can use Generative Fill to create a new object and place it in the image.
    • Change the style of an image: If you want to change the style of an image, you can use Generative Fill to apply a new style to the image.

    Generative Fill is a powerful new tool that can help you create more realistic and creative images. If you’re a Photoshop subscriber, I encourage you to try out the Generative Fill feature and see what you can create.

    Read all the detail on Adobe’s Photoshop blog.

    Update: Here’s another test.. I asked it to create a slip-n-slide down the street, and I’m pretty impressed with the results. Creating this image manually would involve hours of work in a 3D modelling application, then texturing, lighting, then shadows, getting the exact right orientation to match the vanishing point and ensuring it blends into the lighting and colour. Adobe Photoshop did this in about 10 seconds.

    Jason Cartwright
    Jason Cartwright
    Creator of techAU, Jason has spent the dozen+ years covering technology in Australia and around the world. Bringing a background in multimedia and passion for technology to the job, Cartwright delivers detailed product reviews, event coverage and industry news on a daily basis. Disclaimer: Tesla Shareholder from 20/01/2021

    Leave a Reply


    Latest posts


    Related articles