Kling 4.0

Kling 4.0 is Kling AI's new video model: 30-second clips in a single generation, up to 10 keyframes to steer the action, up to 15 image, video and voice references, and stereo sound with more accurate lip sync.

What's new in Kling 4.0

Up to 10 keyframes

Set key moments with up to 10 keyframe images. You decide what each character is doing, where the scene changes and when each story beat lands; Kling 4.0 fills in the motion between them.

The four keyframes behind this shot
  1. A crescent moon, a ringed planet and stars drawn in light on an open palm
  2. A heart and a spiral drawn in light on a monitor
  3. A cartoon burger in an open fridge
  4. An eye drawn in light on a bedroom wall

Omni Reference with up to 15 inputs

Combine up to 10 images, 5 videos (up to 30 seconds in total) and 7 subjects in one generation. Reference videos steer performance, camera movement and pacing, and a subject can carry its own voice.

Eight-panel reference grid of a lion dancer leaping between rooftop poles
The reference grid behind this clip

Big motion, steady camera

High-speed action, continuous movement, tracking shots and orbiting camera moves stay stable and coherent from start to finish.

Dialogue in many languages

Characters can speak Chinese, English, Japanese, Korean, Spanish, Portuguese, German, French and more, with accents and dialects such as Beijing Mandarin, Cantonese, and British and American English. Kling 4.0 generates the sound in two-channel stereo with more accurate lip sync.

More ways to work with Kling 4.0

Edit a video in place

Add, change or remove subjects and backgrounds in an existing clip, or change its style, weather, colour, materials, shot size and camera angle while the rest of the scene holds steady.

Remix a video you admire

Borrow a reference video's pacing, shot order and delivery, then swap in your own products, characters and assets for social posts and product ads.

Prompts up to 8,000 tokens

Write one line or a full scene breakdown. Kling 4.0 fills in, expands and polishes short prompts.

Readable on-screen text

Text in many languages, emoji and logos stay clear and stable, even through camera moves and scene changes.

Kling 4.0 vs Kling 4.0 Flash

Kling 4.0 vs Kling 4.0 Flash
FeatureKling 4.0Kling 4.0 Flash
Best forLonger, more controlled productionsFast, frequent generation with better value
InputsText, image, first and last frames, up to 10 keyframes, referencesText, a first-frame image, references
Length3–30 seconds3–20 seconds
Resolution720p, 1080p, 4K720p
ReferencesUp to 15 itemsSupported

Kling 4.0 vs Kling 3.0

Kling 4.0 vs Kling 3.0
FeatureKling 4.0Kling v3.0 on YouArt
Length3–30 seconds3–15 seconds
Resolution720p, 1080p, 4K720p, 1080p, 4K
Aspect ratios21:9, 16:9, 1:1, 9:16, auto16:9, 9:16, 1:1
Frame controlFirst and last frames, or up to 10 keyframesFirst and last frames
ReferencesUp to 15 images, videos, subjects and voicesFirst and last frame images only
SoundTwo-channel stereo with lip syncOptional sound effects and ambient audio

Plans and pricing

Create with Kling v3.0 and other models on YouArt from one credit balance.

Basic

For hobbyists and explorers

$9.99/mo
Select Plan
  • 1000 credits
  • Up to ~200 images/month
  • Up to ~332s video/month
  • Intelligent creative agent
  • Video editor
  • Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
  • Latest video models, including Seedance 2
  • Realistic face uploads
  • Voice generation with ElevenLabs
  • No watermark
  • Unlimited template access

Pro

Popular

For creators and pro users

$29.99/mo
Select Plan
  • 3300 credits
  • Up to ~1000 images/month
  • Up to ~1100s video/month
  • Intelligent creative agent
  • Video editor
  • Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
  • Latest video models, including Seedance 2
  • Realistic face uploads
  • Voice generation with ElevenLabs
  • No watermark
  • Unlimited template access

Max

Best Value

For power users and teams

$149.99/mo
Select Plan
  • 18000 credits
  • Up to ~6000 images/month
  • Up to ~6000s video/month
  • Intelligent creative agent
  • Video editor
  • Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
  • Latest video models, including Seedance 2
  • Realistic face uploads
  • Voice generation with ElevenLabs
  • No watermark
  • Unlimited template access

Team

For teams and studios

$329.99/mo
Select Plan
  • 36300 credits
  • Up to ~12000 images/month
  • Up to ~12100s video/month
  • Realistic face uploads
  • Share canvas, workflows, and assets with your team
  • Up to 10 members per team
  • Up to 5 teams
  • Role-based management
  • Team credit management and spending caps
  • Per-member usage tracking

Kling 4.0 FAQ

Kling 4.0 is the latest video generation model from Kling AI, Kuaishou's AI video platform. It makes 3–30 second clips at 720p, 1080p or 4K from text, images, keyframes and references, with two-channel stereo sound and more accurate lip sync.

Kling AI announced Kling 4.0 on September 28, 2026, with the full release scheduled for October 2026. The same day, Kling 4.0 Flash opened for limited early access on Kling's top annual plan. 10-bit HDR output at 1080p and 4K, and extending a video to up to 2 minutes, are planned for later updates.

Kling 4.0 is the full model: 3–30 second clips at up to 4K, with keyframes and up to 15 references. Kling 4.0 Flash is the faster, better-value version for frequent creation, making 3–20 second clips at 720p from text, a first-frame image or references.

Kling 4.0 makes videos of 3 to 30 seconds in a single generation; Kling 4.0 Flash goes up to 20 seconds.

Yes. Kling 4.0 outputs 720p, 1080p and 4K, in 21:9 ultrawide as well as 16:9, 1:1, 9:16 and auto.

Kling 4.0 accepts up to 15 references per generation across images, videos, subjects and voices: at most 10 images, 5 videos with up to 30 seconds combined, and 7 subjects, of which up to 3 can come from video.

Kling 4.0 doubles clip length from 15 to 30 seconds, expands frame control from first and last frames to up to 10 keyframes, and combines up to 15 references in one generation. It also adds 21:9 ultrawide, prompts of up to 8,000 tokens and two-channel stereo sound. 4K output and native audio were already part of Kling 3.0.

No. Kling 4.0 is not yet available on YouArt. You can create with Kling v3.0 today, making 3–15 second clips at up to 4K with first and last frames and optional sound, or try other video models on YouArt.

Inspired by Kling 4.0? Start your next video now

Create with Kling v3.0

Kling is a trademark of Kuaishou Technology or its affiliates. YouArt is an independent platform, not affiliated with or endorsed by Kuaishou or Kling AI. Example videos from Kling AI. Kling 4.0 is not yet available on YouArt.