Adobe has just announced the release of their new Firefly Image 3 Model with improved photorealistic quality, styling capabilities, detail, and accuracy. It also offers a greater variety of options, giving creatives more control and flexibility in their ideation process. The Image 3 Model is now available in beta in the Firefly web app, Adobe Photoshop, and Adobe InDesign.
The Image 3 Model works seamlessly with Adobe's recently released Structure Reference and Style Reference capabilities. This combination delivers exceptional user control and state-of-the-art visual quality. Additionally, the model has an improved ability to take reference images into account with a prompt, reducing the trial and error often associated with writing the perfect prompt.
Another exciting introduction is the Generative Expand feature in the Generative Fill module on the Firefly web app. This feature allows users to change the aspect ratio or size of an original image, providing more creative options.
Adobe has also released a new beta version of Photoshop that includes new features like Text to Image, Generate Similar, Reference Image, and more. These new features aim to streamline the creative process and give users more control over their AI-generated designs.
One of the most exciting additions is the Reference Image tool, which allows users to upload their own images to guide the AI's output. Instead of relying solely on text prompts, users can now provide a visual reference that Photoshop's AI will use to match elements like style and color.
In addition to Reference Image, the Photoshop beta includes several other generative AI tools:
- Generate Background allows users to quickly replace and create new backgrounds for product photography
- Enhance Detail increases clarity and sharpens images.
- Generate Similar uses one of the three images generated by Photoshop's Firefly tools as a reference to produce similar content
- Generate Image enables users to create an entire image from a text description starting with a blank page.
