Best practices for creating custom models

Last updated on Oct 1, 2025

Learn about the best practices to effectively prepare and create custom models.

Pick a strong use case

Use case	Good	Avoid
Lifestyle photography	Clear, in-focus people Natural lighting and authentic expressions Variety of poses and compositions Simple or softly blurred backgrounds	Blurry or pixelated images Harsh filters or extreme color grading Overcrowded scenes or distracting backgrounds Group shots where faces are too small to see clearly
Photoshoot of a person	Sharp, well-lit close-ups and mid-distance shots Variety of poses, expressions, and outfits Consistent lighting and environment Clean or softly blurred backgrounds	Faces too small or partially obscured Heavy shadows or harsh lighting Too many similar shots Blurry or low-quality images
Still life photography	Even, well-balanced lighting and shadows Consistent style and color palette Variety of compositions and arrangements Sharp focus on primary subjects	Low-quality or blurry images Product shots with logos or packaging Distracting props or backgrounds Unrelated or off-theme subjects
Illustrated character	Accurate anatomy and proportions Consistent style and rendering quality Variety of poses and expressions Clear details without visual clutter	Low-quality or incomplete illustrations Inconsistent styles or rendering Limited variety in poses or perspectives Distracting backgrounds or unrelated elements
Iconography	Clear, consistent icon style Medium-to-high complexity designs Consistent lighting and color palette Clean, object-focused compositions	Low-quality or blurry icons Unrelated or off-theme concepts Inconsistent styles or rendering methods Overly specific colors and design elements
Brand illustrations	Accurate anatomy and proportions Consistent style and rendering quality Variety of poses and expressions Clear details without visual clutter	Low-quality or incomplete illustrations Inconsistent styles or rendering Limited variety in poses or perspectives Distracting backgrounds or unrelated elements
3D graphics	Consistent perspective and proportions Cohesive style, lighting, and rendering quality Variety of compositions and angles Clear, uncluttered designs	Low-quality or incomplete renders Inconsistent styles or perspectives Limited variety in angles or compositions Distracting elements or unrelated objects
New brand expression illustrations	Strong, consistent brand style throughout Clear compositions with room to breathe Expressive, on-brand characters and scenes Clean rendering with balanced lighting	Mixed styles or inconsistent perspectives Crowded scenes with unclear focus Off-brand props or unrelated visuals Incomplete or low-quality illustrations
New concepts	Visually distinct and well-executed concepts Consistent structure, lighting, and detail Strong form and clear silhouette High-quality images with clean rendering	Repeated shapes or minor variations Distracting backgrounds or details Incomplete or low-quality renders Mixed rendering styles or effects

Use quality images

Use JPG or PNG files.
Choose at least 10-30 high-quality images that showcase the brand-specific styles and concept subjects you want to achieve.
Capture a varied set of images representing the style or subject.
Ensure that each image file size does not exceed 50 MB.
Ensure the images have a resolution higher than 1024x1024 pixels with a maximum 16:9 aspect ratio for landscape or 9:16 for portrait.
Keep the aspect ratio consistent with the training dataset. If the training set is in portrait, and you generate square images, they will have cut-off issues upon generation.
Crop your sample images to focus on the most important visual elements. For example, exclude images that show a person or character off in the distance with a small face or body.
Include images displaying various viewpoints and backgrounds while maintaining a consistent aesthetic.
Make sure your images don’t include an unintentional pattern that you do not want, such as having a white background in every image.
Remove distracting elements that you do not want the model to learn, such as a collage in the background of a portrait or a hat on a character.

Review Model Tags

Include permanent attributes of the subject or style you're training a model on, such as brown hair for a brunette character.
Do not include changeable attributes in Tags, like what object a character is holding.
Include a minimum of three Model Tags.

Review Captions

Use captions to enhance detail and train the custom models on concepts you want the model to generate.
Keep image captions concrete and descriptive, using language that you will use when prompting with the model.
Vary sentence structure across all your image captions.
Modify auto captions as needed to inform the model of the details of the concept.
The Firefly base model does not know famous people or places, so captions should include descriptions of these places to improve potential outcomes.

Use crisp prompts that align with your training data

Include similar words and phrases in your prompts that you used in captions.
Prompting with concepts that align with what you trained the custom model on better preserves that identity than prompting with unrelated concepts (i.e., asking for a black-and-white illustrated rocketship from a model trained on colorful lifestyle photography).

Use advanced style capabilities to further refine your image

The Visual intensity slider is set to the lowest by default for optimal identity preservation. However, for creative use cases such as Style reference, increasing visual intensity can produce more vibrant results.
When using Composition references for subjects, opt for images with white backgrounds or sketches depicting the subject in the desired pose.

Train Firefly Custom Models

Learn

Learn with step-by-step video tutorials and hands-on guidance right in the app.

Community

Join discussions, find answers, learn from experts, and share your knowledge.

Adobe Home

Access your favorite Creative Cloud apps, services, file management, and more.