Available now

Kling 2.5 Turbo Pro: image to video

By Kuaishou

Kling 2.5 Turbo Pro makes 5 or 10 second clips from a written scene or from a starting image, with an optional end frame.

Model ID
Maker
Kuaishou

Input

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

Example prompt. Edit it or write your own.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The duration of the generated video in seconds

The image to be used for the end of the video

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.

Estimated total · 5 s$0.56

You sign up first. Your settings are kept.

About this model

Overview

Kling 2.5 Turbo Pro renders clips of 5 or 10 seconds in 16:9, 9:16 or 1:1 from a written scene. The image mode animates a photo you upload and can end on a second image of your choice.

A negative prompt keeps unwanted things out of the clip, and a guidance setting decides how closely it follows your words.

What you can build

  • Short product and character clips for social feeds
  • A photo animated toward an end frame you choose
  • Square clips for feeds and vertical ones for stories
  • Two lengths of one idea to compare

Prompting tips

  • Describe the motion and the camera, not what the image already shows.
  • Keep the default negative prompt and add anything that keeps appearing, such as captions or extra hands.
  • Raise the guidance setting when the clip drifts away from your prompt.

What to check

Review faces, hands and camera movement through the full clip. Check that the requested action reaches a useful ending.

Inputs

  • Prompt (required)
  • Image (required): URL of the image to be used for the video.
  • Duration (optional): The duration of the generated video in seconds. Options: 5, 10.
  • Negative Prompt (optional)
  • Cfg Scale (optional): The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. From 0 to 1.
  • Tail Image (optional): URL of the image to be used for the end of the video.

Output and limits

  • Length: 5 seconds to 10 seconds.
  • The clips have no sound; add music or a voice-over separately.
  • 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

  • 1 second: $0.111 / second
  • The total for your settings is rounded up to the next cent.