Kling 3.0

Text and image to video with up to 1080p resolution, sound, and 3–15s duration

Generate
Generate sound effects
Result

Results will appear here

About This Model

Kling 3.0 is the latest video generation model by Kuaishou. It supports both text-to-video and image-to-video generation with significantly improved quality, longer duration range, and higher resolution output compared to previous versions.

Key Features

  • Pro quality (1080p) — Generate videos in up to 1920x1080 resolution
  • Flexible duration — 3 to 15 seconds, with per-second control
  • First and last frame — Upload up to 2 images to control the start and end of the video
  • Sound generation — Optional synchronized audio output
  • Multiple aspect ratios — 16:9, 9:16, and 1:1

Best For

  • High-quality short-form video creation
  • Animating images with precise motion control
  • Social media content with sound
  • Product demos and visual storytelling