Accomplice can now learn new objects, like the little buddha statue I keep on my desk

You can now teach Accomplice entirely new people, places, and things

This is the little buddha statue I keep on my desk:

Buddha statue

This is the little buddha statue I keep on my desk “with wings, by greg rutkowski”:

buddha statue with wings, by greg rutkowski

This is my little buddha statue as a robot, as the statue of Davidriding in a caron a bike and on a skateboard, and playing a guitar:

Lots of buddha examples

With Accomplice’s just released updated support for custom styles, it took just 5 photos at various angles and backgrounds, and a little over 30 minutes of training, for Accomplice to learn how to make these images.

Drag and drop styles

And another really nice thing? You can combine custom styles with an image prompt to get exactly the kind of image you want. Like this one of a guy on a laptop I pulled in via Accomplice’s Unsplash integration:

Unsplash example

And like this one, which is actually an image I had previously created using Accomplice’s Picasso Diffusion style, and then used as an image prompt:

Picasso example

Back in February of this year, Accomplice was the first to launch easy drag-and-drop support for custom styles.

And now it's the first to launch support for custom styles that you can train on entirely new subjects.

With this new feature, it's now possible for Pro and above subscribers to create custom styles around unique subjects that they can consistently use over and over again. For illustrators to create characters in a story. For advertisers to create product advertisements featuring the actual product. The list goes on and on.

Adam

https://accomplice.ai/@adam