Last updated on
Jul. 12, 2024
|
Also applies to Adobe Firefly for enterprise
- Welcome to Firefly
- What's new in Firefly
- Generative credits
- Content Credentials
- Frequently asked questions
- Writing effective prompts
- Create images from text prompts
- Match the style of an existing image
- Match image composition
- Add objects in an image
- Remove objects from an image
- Replace a background
- Expand and change the aspect ratio of an image
- Create text styles and textures
- Recolor vector artwork
- Find inspiration in the Gallery
- Submit your work to the Gallery
- Share your Firefly-generated images
- Save to Creative Cloud Libraries
- Train Firefly Custom Models
- Tips to train Firefly Custom Models
- Create, share, use, and manage Style Kits
- Upload image of an object to generate composite scenes
Get to know Firefly
Using Firefly
Share your work
Enterprise features
- Issues and errors
- Technical requirements
Technical help
Learn how enterprise users can train Firefly custom models to reflect their brand.
Training essentials
To train custom models, gather a diverse and representative data set for better performance and accuracy.
- Choose at least 10 - 30 high-quality images that showcase the styles and concepts you want the model to generate.
- Include various viewpoints and backgrounds while maintaining a consistent aesthetic.
- Crop your sample images to focus on the most important visual elements.
- Ensure the images have a resolution higher than 1024 x 1024 pixels with a maximum 16:9 aspect ratio for landscape or 9:16 for portrait.
- Use JPG or PNG files.
Model-specific best practices
Subject models (tech preview)
Custom models trained on a subject, such as objects, characters, or products, will identify key features of the subject and attempt to replicate it in different positions and environments.
Sample images to use
Sample images to avoid
Look for images with the following characteristics when training a subject model:
- Object consistency: Provide images of the same make and model as your subject. Avoid mixing multiple colors and ensure a common theme or pattern among images for effective learning.
- Object focus: Use images of the subject in clear focus without unnecessary distractions. The subject should occupy at least 25% of the image's area.
- Environmental context: Provide images of the subject in different views and contexts, showing it in a variety of lighting conditions. While images with white or transparent backgrounds can be used, it's best to have a mix with more complex surroundings as well.
Style models
Custom models trained on a style will identify the look and feel of the assets to generate similar images when prompted.
Sample images to use
Sample images to avoid
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.