Adobe Teams With OpenAI And Google To Turbocharge Firefly AI Image Tool
According to Adobe, Firefly Image Model 4 is the "most controllable and most realistic Firefly image model yet.” This model offers creatives more control over “the structure and style of outputs, camera angles and zooms”, according to the company, with the ability to experiment and refine their ideas within the context of the original prompt. The tool also allows creative professionals to crop and rearrange images with increased accuracy and print in larger formats without compromising image quality. Conversely, Image Model 4 Ultra is designed to render “complex scenes with small structures for projects that demand impeccable detail and realism.”

In addition to these new capabilities, the Firefly web app now allows creators to generate images using OpenAI's GPT image generation, Google's Imagen 3 and Veo 2, and Flux 1.1. Adobe also promised to integrate more models from additional partners, such as fal.ai, Ideogram, Luma, Pika, and Runway, in the coming months. Firefly will also add a digital tag indicating whether Adobe models or its partners generated the AI image.
Since these models were trained from Adobe Stock and content from the public domain, Adobe says the content is safe for commercial purposes. Access to all of the new models is available now, though Firefly on the web, and a Firefly mobile app will soon be available for iOS and Android devices.
Top Image Credit: Adobe