Firefly is Adobe’s stab at generative AI. I had a quick look at it an and am pretty impressed.

Most current AI image generators make either very cute artificial / fantasy / cartoon style photos, or allow you to create crazy / unreal compositions. For example: creating compositions you would not normally see (an elephant riding a bike), or mixing styles (the US president soloing on a guitar in the style of Van Gogh).

Adobe Firefly is more useful. You can extend backgrounds on existing images, or position objects in pictures. Below are some of my efforts to add a purple cow to an Alpine background.

Here is a basic background. You can now add an object in it. This is the first result after prompting “purple cow”

The placing of the cow is very good, the purple cow itself is totally unrealistic, probably because “purple cow” in itself is not a concept that is very common. You can select alternative versions of the cow that are more realistic (and less purple):

It’s pretty good (although not perfect). Here is the layer that the app generated on top of the background image (I disabled the background layer)

The best feature of the app might actually be the extension of backgrounds. See the example below, the area to the right was added automatically.

Firefly is part of a beta version of Photoshop (it will soon appear in other Adobe apps as well), and as a result requires a bit of Photoshop skill to use it (which will be a drawback from many). You can also access its features via the web interface. Results are pretty good (you can see that Adobe is very good at separating the foreground and background of the image), but the style is still slightly cartoonish.

Why is the quality of Firefly better than other image generators such as DALL-E or Midjourney? Adobe trained its model purely on high quality stock images rather than relatively random internet content.

You can see where this all is going. The quality of images will increase as people get better in feeding quality data in models. Not only stock images, but maybe you can actually analyse entire movies that give you the context of a visual, plus the same image with objects positioned differently. And that I think is the second area for improvement, describing a required composition (background, position of objects, lighting, camera view, etc.).

Check out Adobe Firefly here, including instructions for installation on your computer and/or access the web interface