Kling 4.0
Kling's newest model: clips up to 30 seconds with sound, steered by your own images and videos.
What is Kling 4.0?
Kling 4.0 is Kuaishou's newest video model, built to follow reference images and videos closely over long clips.
On Nsketch it renders 3 to 30 seconds at 720p or 1080p, with audio generated alongside the video. You can give it up to 10 reference images and up to 5 reference videos in one generation.
Pick it when the look has to come from your own material: a character from a few photos, a camera move from a clip you like, a product from its catalog shots. It doesn't take first and last frames or audio references; for those, Seedance 2.5 or Wan 3.0 fit better.
- Provider
- Kuaishou
- Length
- 3 to 30 seconds
- Resolution
- 720p, 1080p
- Aspect ratios
- 16:9, 9:16, 1:1, 21:9
- Audio
- Generated with the video
What you can do with Kling 4.0
Up to 30 seconds
Any length from 3 to 30 seconds in one generation.
10 images and 5 videos
Reference images for people and products, reference videos for motion and camera work.
720p or 1080p
Two quality levels, priced per second.
Sound included
Audio is generated with the video, no separate step.
Prompts to try with Kling 4.0
“The woman from the reference photos walks through a night market in Taipei, stops at a noodle stall, laughs with the cook and carries her bowl to a crowded table. Handheld camera following at shoulder height. Market chatter and sizzling woks. 20 seconds, 9:16.”
Where Kling 4.0 fits best
Characters from a few photos
Turn reference photos of a person into a full scene where they move and act naturally.
Reusing a camera move
Give it a clip whose motion you like and apply it to a new subject.
Product videos from catalog shots
Use existing product images as references and get the product moving in a real setting.
How Kling 4.0 compares
| Model | Length | Top resolution | Native audio |
|---|---|---|---|
| 30 seconds | 1080p | ||
| 30 seconds | 1080p | ||
| 8 seconds | 1080p | ||
| 30 seconds | 1080p | ||
| 15 seconds | 4K | ||
| 15 seconds | 1080p | ||
| 20 seconds | 720p | ||
| 15 seconds | 720p | ||
| 10 seconds | 4K |
Good to know before you generate
- Credits are per second: 25 a second at 720p and 37.5 at 1080p. A 3-second 720p clip costs 75.
- Reference images must be under 10 MB each.
- Each reference video must be 2 to 30 seconds, and 30 seconds in total.
- No first and last frame or audio references on this model.
Start creating with Kling 4.0
Create with Kling 4.0Pick Kling 4.0
Open the video generator; Kling 4.0 is already selected when you come from this page.
Describe it
Write what you want to see, and add reference images if you have them.
Generate
You see the credit cost before you generate, and a failed generation gives its credits back.
What people say about Nsketch
Good app
“I tried the latest templates and the quality is really good”
Nice app
“Very nice app! Good quality and nice Trends”
Fun
“Fun and useful to creating moments that my family can’t make”
Great Quality
“The videos that came have really great quality but they took a little long to generate”
noice
“W nsketch ai best ai tool”
Review for this app
“Amazing app”
Plans and pricing
Every plan includes Kling 4.0. Credits work across every model on Nsketch.
Starter
$11/mo
Billed annually at $132
Get Starter- 600 credits/mo
- 1 hour 5 minutes of TTS / voice cloning
- 2 Concurrent generations
- Up to ~75 Image Generations/month
- Up to ~30 Video Generations/month
- Image Editing
Pro
$33/mo
Billed annually at $399
Get Pro- 2,000 credits/mo
- 4 hours 10 minutes of TTS / voice cloning
- 6 Concurrent generations
- Up to ~250 Image Generations/month
- Up to ~100 Video Generations/month
- Image Editing
Max
$67/mo
Billed annually at $799
Get Max- 4,200 credits/mo
- 7 hours 35 minutes of TTS / voice cloning
- 8 Concurrent generations
- Up to ~525 Image Generations/month
- Up to ~210 Video Generations/month
- Image Editing
FAQ
Questions about Kling 4.0
How long can a Kling 4.0 video be?
From 3 to 30 seconds in a single generation.
What resolution does Kling 4.0 render?
720p or 1080p, in 16:9, 9:16, 1:1 or 21:9, or matched to your reference automatically.
What references does Kling 4.0 accept?
Up to 10 reference images and up to 5 reference videos. It doesn't take first and last frames or audio clips.
Does Kling 4.0 generate audio?
Yes, sound is generated together with the video.
How much does Kling 4.0 cost on Nsketch?
25 credits per second at 720p and 37.5 at 1080p. Reference videos add to the cost, and you see the total before you generate.
Who makes Kling 4.0?
Kuaishou, the company behind the Kling video models.
More video models on Nsketch

ByteDance's longest single take: up to 30 seconds with sound, guided by images, clips and audio you upload.
Google's video model for short, polished clips with dialogue, sound effects and music.
Alibaba's video model for long clips steered by images, videos and audio, from 4 credits a second.

ByteDance's Seedance 2.0 family: Standard up to 4K, plus Fast and Mini for cheaper drafts.