Modality
Also known as: media modality, output modality, generative modality
A modality is the type of media a model produces: image, video, audio, 3D, or text. Generative-media platforms route a single brief across multiple modalities — for example, a still hero image and a 9:16 reel from the same brand kit — without rewriting prompts for each one.
Example
A virtualTryOn run produces an image modality (still try-on) and a video modality (turnaround reel) from the same garment+body inputs — routed through a still-image model and a video model in parallel.
The four modalities that matter for brands
Image is the most mature modality — product shots, lifestyle, banners, try-on. Video took the leap in 2024-2025 with Sora, Veo, Runway Gen-4, and Kling delivering temporally coherent short-form. Audio (voiceovers, music beds, ambient) is now production-ready through token-based generation. 3D matured into a production modality in 2025, compressing modeling timelines from weeks to minutes. Most brand workflows mix at least two of these per campaign.
References
Related terms
Creative App
A creative app is a reusable, named generative-media workflow — productShoot, virtualTryOn, brandFilm — that bundles model routing, prompt scaffolding, brand context, and output formatting into a single callable unit. You call apps, not models, so the same call survives a model upgrade and produces consistent on-brand outputs.
Run
A run is one execution of a creative app — a single call with a brief, a brand kit, and parameters that produces one or more media assets. Every run has an id, a phase stream (queued → composing → rendering → done), and an evaluation score against the attached brand rubric.
Brief
A brief is the natural-language prompt plus structured parameters passed into a creative app. Briefs describe what to make ("linen tee on weathered teak, north light, 35mm") and how to constrain it (variants, ratios, models). Combined with a brand kit and a seed, the same brief produces a deterministic run.