Models

OnVid AI video models

Explore every AI video model available on OnVid — compare capabilities and pick the right one for your next clip.

Native 4K video up to 30 seconds in a single pass, with synced sound and up to 50 reference inputs.

Black Forest Labs' unified image + video + audio model, with clips up to ~20 seconds.

Fast text- and image-to-video with synced native audio, from dialogue and lip-sync to sound effects.

Expressive, lifelike character motion with camera-director controls.

Turn one portrait plus audio into a talking avatar with lifelike lip-sync.

Synced audio and video in a single pass, with strong character consistency.

Cinematic 4K text-to-video with native audio and multi-shot consistency.

Director-style 4K generation with native synced audio and reference consistency.

The first AI video model with native 16-bit HDR, exportable as EXR for pro color pipelines.

Native 2K motion with synced audio and omni-reference — the Hailuo 3 generation.

Precise start-to-end image transitions (Pikaframes) and playful effects.

Fast multi-shot social clips with native audio, up to 1080p.