Adobe

Get help faster and easier

New user?

Adobe MAX 2024

Adobe MAX
The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX

The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX 2024

Adobe MAX
The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX

The Creativity Conference

Oct 14–16 Miami Beach and online

Last updated on Sep 11, 2024

Explore strategies and best practices for training custom style models.

Try it in the app
Create a custom model with images of your brand's assets in a few simple steps.

Custom models trained on a style will identify the look and feel of the assets to generate similar images when prompted.

Images

To train an effective style model:

  • Provide similar aesthetics: Include images that show various scenes and objects while maintaining the same look and feel.
  • Use various images: Use as many images as you can to prevent the model from focusing too much on unwanted objects or subjects.
  • Avoid any fixed phrases: A fixed pattern has a bigger weight than other phrases. For example, if every caption contains "The background is solid black" or “cute cartoon styles” the model will depend on this phrase, and any testing prompt without it will not generate the desired results. 

  Sample images to use

Four panels of illustrations, each showing various people engaged in data analysis and presentation activities. There are geometric design elements and other elements like large pie charts and bar graphs. This is an example of the correct set of images that can be used to train style custom models in Firefly.
Use a set of images with the same colors and aesthetic for best results.

  Sample images to avoid

Four panels of illustrations, each showcasing distinctly different styles. This set of images is unsuitable for training style custom models in Firefly, as there is no consistent style or aesthetic across the four examples.
Images with varying colors and aesthetics can result in less effective models.

Captions

  • Keep image captions short and concise. We recommend no more than 15-18 words. 
  • The captions should call out details that allow Firefly to gain context about the style. 
  • Focus on what is unique about each image using terminology that your Generators will use when prompting, such as “human figure” or “pink bulleted circles.”
  • Avoid any fixed phrases, as a fixed pattern has bigger weight than other phrases. For example, if every caption contains "The background is solid black" or “cute cartoon styles” the model will depend on this phrase, and any testing prompt without it will not generate the desired results. 

More like this

Join our community to connect, learn, and engage

For inspiration, expert tips, and solutions to common issues, visit Discord or the Adobe Firefly Community forum. Connect with our team and fellow users to exchange ideas, share your creations, stay updated with the latest features and announcements, and provide feedback.

 Adobe

Get help faster and easier

New user?

Adobe MAX 2024

Adobe MAX
The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX

The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX 2024

Adobe MAX
The Creativity Conference

Oct 14–16 Miami Beach and online

Adobe MAX

The Creativity Conference

Oct 14–16 Miami Beach and online