Adobe Firefly encompasses all the creative generative AI models that will show up in Adobe products. Firefly’s first model trains on a database of Adobe Stock images, openly licensed content, and public domain content where copyright expired to turn text descriptions into AI creations. Starting with models that allow you to generate an image from a text prompt and adding an image to text, Firefly can create a watercolor of a sailboat at sunset or turn the letters of your favorite pizza parlor’s name into an actual pizza.
And that’s just the beginning. Many AI image generators do just that, generate images. Adobe Firefly will eventually provide many generative AI tools. The models that let users change the mood of a video, remove distractions from photos, test out design options, add texture to 3D objects, and add new elements to illustrations are all in the works. As is the capability to do even more tweaking and personalizing to Firefly AI creations in other Creative Cloud tools like text effects in Adobe Express, generative fill in Photoshop, and generative recolor in Illustrator.
Outside of DALL·E, it is important to know the pros and cons of other generative AI tools such as Stable Diffusion and Midjourney when compared against Firefly.