minimaxiH3 Get access
KuaishouImage-to-videoVendor content policy applies

Kling Video O3 Pro Reference-to-Video

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references. Professional quality with up to 7 reference images and optional video input.

$0.14per secondStarting price at the base resolution and quality tier.
$1.14Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “Referring to the image, describe how the people in the video are dressed.”

What it does

Kling Video O3 Pro Reference-to-Video, in practice.

Kling Video O3 Pro Reference-to-Video generates premium video from reference images with optional video guidance. Upload reference images to establish character identity and appearance, optionally provide a reference video for motion guidance, and describe the scene — the model produces top-tier cinematic video with identity consistency.

Run Kling Video O3 Pro Reference-to-Video

from $0.14/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
aspect_ratio
shot_type
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
aspect_ratioThe aspect ratio of the generated video.16:9 9:16 1:1
durationThe duration of the generated media in seconds (3-15).3 4 5 6 7 8 9 10 11 12 13 14
imagesReference images. With a reference video: image elements ≤ 4; without a reference video: ≤ 7
keep_original_soundWhether to keep the original sound from the reference video.default True
promptThe positive prompt for the generation.
soundWhether to generate audio for the video.default
videoThe reference video URL.
multi_shotWhether to enable multi-shot generation.default
shot_typeMulti-shot mode. customize = caller provides per-shot prompts; intelligence = model auto-splits the top-level prompt into shots. Required when multi_shot=true.customize intelligence
multi_promptPer-shot storyboards. Required when multi_shot=true and shot_type=customize. Sum of each shot's duration must equal the top-level duration; each shot duration must be >= 1.
elementsSubject references . Each item either references an existing subject by element_id, or creates a new one inline with element_name + reference_type + frontal_image / refer_images / refer_videos (At

Sample prompt

The prompt behind the sample.

Referring to the image, describe how the people in the video are dressed.
aspect_ratio: 16:9duration: 5keep_original_sound: Truesound:

FAQ

Short answers.

How much does Kling Video O3 Pro Reference-to-Video cost?

Pricing starts at $0.14 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $1.14. Usage is billed per request from your balance — no subscription.

Does Kling Video O3 Pro Reference-to-Video run uncensored here?

No. Kuaishou applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Kling Video O3 Pro Reference-to-Video for everything else it does well.

What does Kling Video O3 Pro Reference-to-Video take as input?

It is a image-to-video model. Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references. Professional quality with up to 7 reference images and optional video input.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Kling Video O3 Pro Reference-to-Video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models