Available now

Kling 3 4K: text to video

By Kuaishou

Kling 3 4K renders clips of 3 to 15 seconds with sound straight at 4K, from a written scene or from a start image with an optional end image.

Model ID
Maker
Kuaishou

Input

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

Text prompt for video generation.

Example prompt. Edit it or write your own.

The duration of the generated video in seconds

The aspect ratio of the generated video frame

Additional settings

The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.

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$3.33

You sign up first. Your settings are kept.

About this model

Overview

Kling 3 4K outputs 4K video directly rather than upscaling a smaller render. Clips run 3 to 15 seconds in 16:9, 9:16 or 1:1, with generated sound on by default; spoken lines can be in English or Chinese.

The image mode starts from your picture and can finish on an end image. In both modes a shot type setting lets the model plan the shots itself, and a negative prompt and a guidance scale tune how closely it follows you.

What you can build

  • Footage for large screens and presentations
  • Product shots with room to crop in the edit
  • A move from a start image to an end image at full detail
  • Short spoken scenes in English or Chinese

Prompting tips

  • Write English dialogue in lowercase and keep capitals for acronyms and names, so the voice reads them right.
  • Raise the guidance scale toward 1 when the clip must follow the prompt closely; lower it for looser motion.
  • Pick the intelligent shot type to let the model cut the scene into shots on its own.
  • Turn sound off when the clip goes under your own music or voice-over.

What to check

Inspect fine moving detail at full size, particularly faces and hard edges. Review generated speech and the closing frame.

Inputs

  • Prompt (optional): Text prompt for video generation.
  • Duration (optional): The duration of the generated video in seconds. Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
  • Generate Audio (optional): Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.
  • Shot Type (optional): The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. Options: customize, intelligent.
  • Aspect Ratio (optional): The aspect ratio of the generated video frame. Options: 16:9, 9:16, 1:1.
  • 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.

Output and limits

  • Length: 3 seconds to 15 seconds.
  • Aspect ratios: 16:9, 9:16, 1:1.
  • Sound can be generated together with the video.
  • 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: $0.6656 / second
  • The total for your settings is rounded up to the next cent.