AI video model · by Kuaishou
Kling AI video generator
Kling is the video model family from Kuaishou. On MotionLab you can run the current Kling versions from text or from a start image, compare them with other video models on the same page, and keep every take in one library.
Kling variants available now
These are the Kling variants currently enabled on MotionLab and the settings each one accepts. The table is generated from the live model catalog, so it changes when a variant is added, updated or paused.
| Variant | Modes | Duration | Resolution | Aspect ratios | Audio / end frame |
|---|---|---|---|---|---|
| Kling 4.0 Keyframes | Image to video | 3–30s | 720p · 1080p | auto · 16:9 · 9:16 · 1:1 · 21:9 | Native audio · End frame |
| Kling 4.0 References | Reference to video | 3–30s | 720p · 1080p | auto · 16:9 · 9:16 · 1:1 · 21:9 | Native audio · No end frame |
| Kling V3 Pro | Image to video · Text to video | 3–15s | 1080p | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · End frame |
| Kling V3 4K | Image to video · Text to video | 3–15s | 4K | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · End frame |
| Kling Video V3 Turbo Standard | Text to video · Image to video | 3–15s | 720p | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · No end frame |
| Kling Video V3 Turbo Pro | Text to video · Image to video | 3–15s | 1080p | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · No end frame |
| Kling Video V3 Standard (Motion Control) | Motion control | 1–30s | 720p | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · No end frame |
| Kling Video V3 Pro (Motion Control) | Motion control | 1–30s | 1080p | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Native audio · No end frame |
What to use Kling for
- Character and people shots where you want readable motion and expressions.
- Image-to-video from an approved still, so composition and styling stay locked.
- Higher-resolution deliverables when the 4K variant is available for your settings.
- Short product, fashion and lifestyle clips cut into social edits.
How to use Kling on MotionLab
- Sign in and open the video creation page.
- Choose a Kling variant in the model picker. Only the variants listed above are shown.
- Write your prompt, add a start image or references if the mode needs them, and pick duration, resolution and aspect ratio.
- Check the credit cost shown for your settings, then generate. Failed jobs are refunded automatically.
- Download the result or keep refining it in your library.
Kling prompt tips
- Describe one main action and one camera move; stacking several moves in one clip tends to blur both.
- With image-to-video, describe what changes, not what is already visible in the frame.
- Name the pace explicitly — slow, steady, sudden — so motion speed matches your edit.
- Keep the subject's identity details consistent across siblings when you need a matched set.
More technique in the MotionLab prompt guide and the camera motion guide.
Compare Kling with other models
Kling questions
Can I use Kling for image-to-video?
Yes. Upload or pick a start image in the MotionLab video page and choose a Kling image-to-video variant. The table on this page lists the Kling modes that are currently enabled.
How much does Kling cost on MotionLab?
Kling generations spend MotionLab credits from the same wallet used by every model on the site. The credit cost for your exact settings is shown before you generate, and a job that fails is refunded automatically. Credit packs are listed on the pricing page.
Do I need a separate Kling account or API key?
No. MotionLab runs Kling for you: sign in, pick the model in the create page and generate. Your results are saved to your MotionLab library next to work from every other model.
Which Kling version should I choose?
Start with the standard Pro variant for drafts and switch to a higher-resolution variant for the take you will deliver. The specs table shows which resolutions and durations each enabled variant accepts right now.