Kling Video O3 Pro Reference To Video: Cinematic Identity-Locked Video Generation on Models and API | RunComfy

Kling Video O3 Pro Reference To Video is Kuaishou's Pro-tier reference-driven entry in the O3 family. It generates a 3 to 15 second cinematic clip from a prompt while preserving the identity of the people, props, or styles you supply as reference images, with an optional reference video for motion or style guidance. The result keeps consistent characters and looks across frames at the top of the O3 fidelity range.

You can attach reference images of characters, props, or art styles, plus an optional reference video for motion or style transfer. Without a reference video, up to 7 image references are supported; with a reference video, image references are capped at 4. In the prompt, you bind subjects to specific images by position — for example, "Figure 1 stands next to Figure 2" — so Kling Video O3 Pro Reference To Video knows which subject to place where.

Compared with the Standard reference-to-video tier, Kling Video O3 Pro Reference To Video targets a higher fidelity ceiling on motion, lighting, and identity stability, which suits hero and broadcast cuts based on available provider information. Standard is positioned for iteration and high-volume drafts at a lower per-second rate. The control surface — prompt, references, aspect ratio, duration, sound, shot type — is the same, so prompts and references move between tiers without rework.

Film teams, ad agencies, brand studios, e-commerce video producers, and product groups use Kling Video O3 Pro Reference To Video to produce identity-locked spots from existing stills — different scenes, props, or moods without reshoots. It also fits spokesperson content, premium concept reels, multi-character storytelling beats, and style-consistent campaign cutdowns. Developers integrate it into automated pipelines that turn a brief plus a few references into a finished short clip.

The model requires a prompt; references and the reference video are optional but recommended. Image references are capped at 7 (or 4 alongside a reference video), aspect_ratio accepts 16:9, 9:16, or 1:1, duration is an integer between 3 and 15 seconds, and shot_type accepts customize or intelligent. Sound and keep_original_sound are booleans, and sound generation only applies when no reference video is supplied. For other constraints such as resolution or file format, check the current RunComfy parameter panel for the exact limits, since they may vary by provider settings.

Yes. You can prototype Kling Video O3 Pro Reference To Video in the RunComfy AI Playground Web UI — dialing in references, prompt phrasing, aspect ratio, duration, and audio toggles — and then call the same model via the RunComfy API with identical parameters. This keeps creative iteration in the browser while production runs in code, without changing how the model behaves.

Generations consume usd / credits from your RunComfy balance. Kling Video O3 Pro Reference To Video bills $0.112 per second without sound, $0.135 per second when synthesized sound is enabled, and $0.168 per second when a reference video is supplied (the reference-video rate overrides the sound multiplier). As examples, 5 seconds without sound is around $0.560, 10 seconds with sound is around $1.350, and 15 seconds with a reference video is around $2.520. New users typically get a free trial usd amount; refer to the Generation section of the model page for the latest rates.

Kling Video O3 Pro Reference To Video responds best to clear, specific prompts that bind references to roles using "Figure 1", "Figure 2", and so on, then describe the action, environment, and camera move. Concrete cues like "50mm slow dolly-in", "golden hour rim light", or "neon practicals" anchor look and motion better than vague mood words. For complex scenes, use multi-prompt segments to separate beats so transitions stay clean within a single clip.