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.
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.
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.




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.

High-speed action, continuous movement, tracking shots and orbiting camera moves stay stable and coherent from start to finish.
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.
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.
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.
Write one line or a full scene breakdown. Kling 4.0 fills in, expands and polishes short prompts.
Text in many languages, emoji and logos stay clear and stable, even through camera moves and scene changes.
| Feature | Kling 4.0 | Kling 4.0 Flash |
|---|---|---|
| Best for | Longer, more controlled productions | Fast, frequent generation with better value |
| Inputs | Text, image, first and last frames, up to 10 keyframes, references | Text, a first-frame image, references |
| Length | 3–30 seconds | 3–20 seconds |
| Resolution | 720p, 1080p, 4K | 720p |
| References | Up to 15 items | Supported |
| Feature | Kling 4.0 | Kling v3.0 on YouArt |
|---|---|---|
| Length | 3–30 seconds | 3–15 seconds |
| Resolution | 720p, 1080p, 4K | 720p, 1080p, 4K |
| Aspect ratios | 21:9, 16:9, 1:1, 9:16, auto | 16:9, 9:16, 1:1 |
| Frame control | First and last frames, or up to 10 keyframes | First and last frames |
| References | Up to 15 images, videos, subjects and voices | First and last frame images only |
| Sound | Two-channel stereo with lip sync | Optional sound effects and ambient audio |
Create with Kling v3.0 and other models on YouArt from one credit balance.
For hobbyists and explorers
For creators and pro users
For power users and teams
For teams and studios
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.