KLING · 4.0

Kling 4.0: one take, up to 30 seconds

Kling 4.0 is the fourth generation of Kuaishou's Kling family and its biggest step yet: single takes from 3 to 30 seconds with native stereo audio, up to 10 keyframes to direct the action, and cinema-grade output up to 4K in 10-bit HDR. Available now in Picsart's AI Playground.

Start
End
Ref
Describe your scene - one take, up to 30 seconds...

Videos made with Kling 4.0

Kling 4.0 sample clip (placeholder creative)
Kling 4.0 sample clip (placeholder creative)
Kling 4.0 sample clip (placeholder creative)
WHAT IS KLING 4.0

What is Kling 4.0?

Kling 4.0 is Kuaishou's next-generation multimodal video model, launched in October 2026. It generates from text, an image, or a first and last frame, holds a single continuous take anywhere from 3 to 30 seconds - double the previous ceiling - and reads prompts up to 8,000 tokens. Give it one line and it expands the idea with a director's eye; give it a detailed script and it follows it faithfully - in styles from vlogs and documentary realism to clay animation, glitch art, felt textures, and 3D cyber aesthetics.

  • Text or image to video
  • 3 to 30 seconds per take
  • Keep editing in Picsart
What is Kling 4.0 (placeholder creative)
UP TO 10 KEYFRAMES

Direct the shot with up to 10 keyframes

Pin the moments that matter and Kling 4.0 builds the motion between them. Two keyframes set the beginning and end, five control the turning points, ten build a full storyboard sequence - while characters, style, and scene elements stay consistent across every frame. Camera direction matured with it: push-ins, pull-outs, pans, tracking and orbit shots render stable and natural, and even high-speed action - running, chases, fast rotations - holds its structure.

Keyframe control in Kling 4.0 (placeholder creative)
4K, 10-BIT HDR, STEREO

Cinema-grade picture and sound, out of the box

Output reaches 4K with 10-bit HDR at 1080p and 4K, so backlit shots, night scenes, and neon keep their highlight and shadow detail - and 21:9 ultrawide opens the frame for cinematic composition. Every clip renders with two-channel stereo and tighter lip-sync, and characters read as genuinely expressive: facial detail, lighting, and texture feel natural, so a glance or a moment of hesitation carries the emotion on screen. On-screen text, logos, and emojis stay sharp through camera moves in nine languages.

4K HDR output with stereo sound in Kling 4.0 (placeholder creative)
INSIDE AI PLAYGROUND

Kling 4.0 in Picsart AI Playground

Kling 4.0 lives in Picsart's AI Playground alongside 150+ other AI models, so you can generate a 30-second take and keep building on it right next to your other creative tools - no third-party API keys or separate subscriptions. Reach it whichever way you work: on the web, in the desktop app, and via CLI, MCP, REST API, and SDK, so a shot you prototype here drops straight into an automated pipeline.

Kling 4.0 inside Picsart AI Playground (placeholder creative)

What you can do with Kling 4.0

Six ways to put 30-second takes to work.
Short drama scene with dialogue (placeholder creative)
  • Hold one continuous take for up to 30 seconds with stereo sound and lip-synced dialogue - a complete story beat with no stitching, built for short dramas and TVC-style ads.

How to generate video with Kling 4.0

Describe the scene, set your length and format, and generate - all in Picsart.

How to

Describe or upload

Open Kling 4.0 in Picsart AI Playground and describe your scene - a one-line idea the model expands, or a detailed script up to 8,000 tokens. You can also start from an image or a first and last frame.

Step 1: Describing a scene for Kling 4.0 (placeholder creative)

Kling 4.0 FAQ

Answers about generating video with Kling 4.0 in Picsart.

  • Kling 4.0 is Kuaishou's fourth-generation multimodal video model, launched in October 2026. It generates video from text, images, or a first and last frame, with native stereo audio, keyframe control, and multilingual voices and on-screen text.

Pricing

Generate a few takes or build a repeatable video workflow for campaigns, social, and film projects.

SAVE UP TO 50%

Pro

Most popular

AI tools for everyday creative work.

$15 $10.5/mo
Billed yearly
You save $54 with yearly
Trending models
Full access
  • Seedance 2.04K 15s
  • Nano Banana Pro4K
  • MiniMax H32K 15s
  • Kling 3.04K 15s
  • Access to all photo & video editing features
  • Advanced background & object removal
  • Parallel video generations with the world's most powerful AI video models
  • Unlimited image generations with Flex.2 Klein
  • 1-tap image enhancer
  • Millions of stock photos & Getty video clips
  • Selection of trendy fonts, text styles & stickers
  • Thousands of premium templates
  • Support for 3+ brand kits
  • Bulk edit up to 50 images at once
  • 100 GB of cloud storage
New features:
  • 15+ creative AI agents that plan, execute, and deliver — across video, brand, localization, and more
  • Auto-generate content from your terminal or agent with the Picsart CLI
  • Use Picsart inside Claude Code, Cursor, and ChatGPT via MCP

Ultra

Most powerful

Heavy AI usage for creators & teams.

$45 $24.5/mo
Billed yearly
You save $246 with yearly
Trending models
Full access
  • Seedance 2.51080p 30s
  • Nano Banana Pro4K
  • MiniMax H32K 15s
  • Kling 3.04K 15s
  • 200+ leading AI video, image, and audio models (Kling 3.0, Nano Banana, MiniMax H3, Seedance 2.5 & more)
  • Parallel video generations with the world's most powerful AI video models
  • Early access to advanced AI features
  • Unlimited image generations with Flex.2 Klein
  • Option to buy add-on credits that never expire
  • Up to 6.5 million Getty stock videos
  • Bulk edit up to 100 images at once
  • Support for 10+ brand kits
  • Create ad variations & localize
  • Track ads performance
  • Add team seats
  • 300 GB of cloud storage per seat
New features:
  • 15+ creative AI agents that plan, execute, and deliver — across video, brand, localization, and more
  • Auto-generate content from your terminal or agent with the Picsart CLI
  • Use Picsart inside Claude Code, Cursor, and ChatGPT via MCP