Glossary
Reference image
Also known as: ref image, image-to-image input
An image uploaded alongside the prompt to condition the generation. The model preserves visual properties — composition, color palette, subject likeness, framing — from the reference in the output.
In depth
What it means in practice
Reference image conditioning is one of two main control surfaces for image models (the other is text prompting). Different models weight different aspects of the reference. Kling v2.6 Pro is class-leading at preserving color and subject likeness; Nano Banana 2 is class-leading at preserving identity across multi-panel outputs; FLUX preserves composition and lighting with high fidelity.
For brand work animating an existing logo, character, or product photo, reference image conditioning is what makes the output recognizable as "yours" rather than a generic generation. The trade-off: more reference weight = less creative variance.
Related
Prompt
The text instruction given to an AI model that describes what to generate. For image and video models, prompts mix subject description, style direction, camera or composition hints, and optional negative prompts.
Identity preservation
A model's ability to keep a person's face or a character's appearance consistent across multiple generations from the same reference. Critical for multi-panel collages and character-driven content.
Image-to-video
A generation mode where the input is a still image and the output is a video animating that image. Often paired with a text prompt describing the desired motion.