Firefly is powerful and I won’t be able to describe everything you can do with it. Instead, I’ll walk you through the basic process of generating an image using an AI model, and then using that image as a starting frame to generate a brief, looping video.
At the top, select Up-to-date. You can create a modern file or generate a modern file. For example, creating a file allows you to upload a photo and utilize generative AI to edit it, while generating a file creates that image from scratch with an AI model. In this example, select Picture in the generation section.
On this modern screen, you’ll see a chatbot-like suggestion box along with some general settings. At the top of the sidebar, you can select your model and aspect ratio, and upload a reference image. If you want to achieve something specific, please upload a reference image. In the prompt box you will see how much credits it costs to generate and also toggle the prompt suggestion. To choose Cause after entering the prompt.
Now you have the picture, but this is really just a starting point. If you don’t like the result, select the three dots next to the image and select Generate more for more options. If the image is close but not perfect, you can hover over it and select Edit, and then select Exploit as reference image to feed them back into the AI model. In the same menu you can also select Edit image, which will allow you to adjust the generated image by talking to the AI model.
Once you have an image you like, you can return to the main Firefly screen by clicking the icon in the upper left corner. Adobe keeps a record of your file generation history in Firefly so you can recall your generated assets later. Now that we have our starting frame, we will generate the video. To choose Up-to-date again and select Video.