Models

OnVid AI video models

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

Any input — text, image, audio, or video — into an edited clip, refined by conversation.

Gemini 3 Pro Image — photoreal 4K stills with accurate, legible text rendering.

Animate a still image into a short clip in Midjourney's signature painterly style.

fal's speed-tuned post-train of MiniMax H3 — #1-ranked quality and native audio, a 5s 768p clip in under 3 seconds.

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

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

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

Up to 16s of continuous 1080p video with native synced audio and lip-sync.

Native audio and dialogue generated in the same pass as the video.

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

Sharp, physically accurate motion in crisp 4K.

Leaderboard-topping video with native audio, reference control, and social-ready templates.