Kling O3 Standard Video Reference

Kling O3 Standard Video Reference by Kuaishou generates a new 720p shot that follows the style and camera motion of a reference video, optionally guided by reference images.
30% OFFkwaivgi/kling-video/o3/standard/video-to-video

Kling O3 Standard Video Reference by Kuaishou generates a new 720p shot that follows the style and camera motion of a reference video, optionally guided by reference images.

Try the model

Playground

Open playground
Input
Text prompt for video generation. Reference video as @Video1.
Reference video URL. Only .mp4/.mov formats, 3-10s duration, 720-2160px resolution, max 200MB.
Additional Settings More

Customize your input with more control.

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.
Video duration in seconds (3-15s for reference video). Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
The type of multi-shot video generation.
Whether to keep the original audio from the reference video.
The aspect ratio of the generated image. Allowed values: 16:9, 9:16, 1:1.
30% OFF
Result
Example
  1. What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.441. Final charges follow the model’s billing rules below.

Kling O3 Standard Video Reference

Kling O3 Standard video reference: generate new shots that follow the motion and camera language of a reference video, while the prompt and optional reference images set the new scene and look.

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 2,500 characters.
imagesimage URL[]—Reference images, referred to as @Image1, @Image2, … in the prompt.
videovideo URL, required—Reference video, @Video1 in the prompt.
duration3–15—Output length; omit to match the reference.
shot_typestringcustomizecustomize follows your multi_prompt shot list; intelligent lets the model plan the cuts.
keep_audiobooleantrueKeep the source video's audio track.
aspect_ratio16:9 / 9:16 / 1:116:9Output frame shape.

Billing

You pay $0.126 per output second. Without duration the output matches the reference length; the quote assumes 5 seconds.

OutputPrice
3s$0.378
5s$0.63
10s$1.26
15s$1.89

Failed runs are not charged.

Prompting

  • Describe the new scene; the reference video supplies motion and camera.

Limits

  • Clips are 3–15 seconds.

Also on SandBase

Other Kling O3 Standard endpoints and tiers: kwaivgi/kling-video/o3/standard/text-to-video, kwaivgi/kling-video/o3/standard/image-to-video, kwaivgi/kling-video/o3/standard/reference-to-video, kwaivgi/kling-video/o3/standard/edit, kwaivgi/kling-video/o3/pro/video-to-video, kwaivgi/kling-video/o3/4k/video-to-video.