Adobe has announced the integration of its AI image generator, Firefly, into its popular software, Photoshop. The new feature, called Generative Fill, enables users to easily extend images, add or remove objects, and enhance their creative workflow using text prompts. While currently available in beta, Generative Fill is expected to have a full release in Photoshop later this year.
Generative Fill functions as a regular tool within individual layers of a Photoshop image file. Whether expanding image borders or generating new objects, users are presented with three options to choose from. While leaving the prompt blank allows the system to expand the image automatically, providing direction leads to better results. Comparable to Photoshop's Content-Aware Fill, Generative Fill offers users enhanced control and creative possibilities.
AI Model Trained on Selected Image Material
Firefly's training data is another essential aspect of its functionality. Adobe emphasizes that the model is exclusively trained on content for which the company possesses the rights to use, such as Adobe Stock images, openly licensed content, and copyright-free material. This ensures that any content generated using Generative Fill is safe for commercial use, providing reassurance to creative professionals and agencies that have been hesitant to adopt AI tools due to potential legal complications.
Additionally, Generative Fill incorporates Content Credentials, a “nutrition label” system that attaches attribution data to images, informing viewers if the content was created or edited using AI. By visiting verify.contentauthenticity.org, users can access an overview of information about the image's Content Credentials.
While Generative Fill is currently available in the beta version of Photoshop, users can try it out by downloading the Photoshop desktop beta app or as a module within the Firefly beta app. Adobe anticipates a full release of Generative Fill on the public Photoshop app in the second half of 2023.
Adobe's integration of AI-powered tools, including Firefly, into its products reflects the company's commitment to innovation. With features like higher-quality object selections in Photoshop and vector recoloring in Illustrator, Adobe continues to expand its AI capabilities. Furthermore, Adobe has plans to integrate Firefly with Adobe Express, a cloud-based design platform, but a release date for that integration has not yet been confirmed.
Overall, Adobe's introduction of Generative Fill and Firefly's integration into Photoshop signifies a significant step toward enhancing creativity and productivity for digital artists and designers. As AI becomes increasingly embedded in mainstream applications, users can expect new possibilities for image editing and content generation.
Generative AI Is Revolutionizing Image Editing
Adobe´s efforts to integrate AI-powered tools into its products is a logical step, as new AI powered techniques and services enter the field of image editing and manipulation. Just a few days ago, researchers presented DragGAN as a new a new AI-powered approach to image editing using generative priors and point-based editing. Its point-based editing technique allows users to make more precise modifications to specific image areas without affecting the entire image. DragGAN pushes the boundaries of traditional image manipulation tools as itt offers users the capability to edit images as if manipulating a 3D model, resulting in more granular control and precision.
Image generation is a branch of generative AI that has become mainstream in the last few months. Google also showed an image generating AI known as MediaGen that is similar to other image/video AI such as MidJourney and Microsoft's Bing Image Creator.
Bing Image Creator is one of Microsoft's latest tools for AI and web services. The AI can create images based on simple words or phrases, such as animals, objects, landscapes, or abstract concepts. However, the tool also has some limitations and restrictions. For example, it refused to make an image based on the word “Bing” when it was first released.
Image Creator launched last month as an image-search accompaniment for Bing Chat. It is powered by OpenAI and Microsoft's DALL-E image processing natural language AI model.
Two of the biggest tech companies – and the leaders in mainstream AI development – are now in the AI image space. Are Microsoft and Google direct competitors to MidJourney? Not yet and not quite. While Bing Image Creator is already available, as its name suggests, it is more focused on crafting images for users rather than art in the way Midjourney does.