Available now

Kling 3 Standard: motion control

By Kuaishou

Kling 3 Standard makes 3 to 15 second clips with sound from a written scene or a starting image, and can copy the movement of a reference video onto your character.

Model ID
Maker
Kuaishou

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

Reference image. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Uploading a file needs an account. Create account

MP4, WebM · up to 100 MB

Additional settings

Whether to keep the original sound from the reference video.

Price$0.1997 / second

You sign up first. Your settings are kept.

About this model

Overview

Kling 3 Standard renders clips of 3 to 15 seconds in 16:9, 9:16 or 1:1, with voices and effects generated together with the picture. One prompt can become several shots, laid out by you or by the model.

The image mode starts from a photo and can end on a second one. Motion control takes a reference video and a picture of your character, and moves the character the way the person in the video moves.

What you can build

  • Short scenes with spoken lines and sound
  • Clips with several cuts from one prompt
  • A product photo that turns into a moving shot
  • Characters that repeat a dance or gesture from a reference video

Prompting tips

  • Write spoken lines into the prompt and say who speaks; voices come out in English or Chinese.
  • Choose the intelligent shot type when you would rather not plan the cuts yourself.
  • For motion control, use a reference video in which the person's whole body or upper body stays in view.

What to check

Inspect the action from beginning to end. Check changing faces, body proportions and any generated dialogue.

Inputs

  • Prompt (optional)
  • Image (required): Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area.
  • Video (required): Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction.
  • Keep Original Sound (optional): Whether to keep the original sound from the reference video.
  • Character Orientation (required): Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s). Options: image, video.
  • Elements (optional): Optional element for facial consistency binding. Upload a facial element to enhance identity preservation in the generated video. Only 1 element is supported. Reference in prompt as @Element1.

Output and limits

  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • per second: $0.1997 / second
  • The total for your settings is rounded up to the next cent.