Kling AI Model Catalog
Overview
Kling AI offers multiple model versions across video generation, image generation, lip sync, virtual try-on, and effects. Each version trades off quality, speed, and cost. This skill is the reference for choosing the right model.
Video Generation Models
| Model ID |
Supports |
Max Duration |
Resolution |
Speed |
Quality |
kling-v1 |
T2V, I2V |
10s |
720p |
Fast |
Good |
kling-v1-5 |
I2V only |
10s |
1080p |
Fast |
Better |
kling-v1-6 |
T2V, I2V |
10s |
1080p |
Medium |
Better+ |
kling-v2-master |
T2V, I2V |
10s |
1080p |
Medium |
High |
kling-v2-1 |
I2V only |
10s |
1080p |
Medium |
High |
kling-v2-1-master |
T2V, I2V |
10s |
1080p |
Medium |
High |
kling-v2-5-turbo |
T2V, I2V |
10s |
1080p 30fps |
Fast |
High |
kling-v2-6 |
T2V, I2V |
10s |
1080p 30-48fps |
Medium |
Highest |
T2V = text-to-video, I2V = image-to-video
Kling v2.5 Turbo (Recommended for Speed)
- 40% faster than v2.0
- Up to 1080p at 30 FPS
- Best cost/quality ratio for production pipelines
Kling v2.6 (Recommended for Quality)
- Native audio generation (voice, SFX, ambient in one pass)
- 1080p at 30-48 FPS
- Set
motion_has_audio: true for synchronized audio
Image Generation Models (Kolors)
| Model ID |
Purpose |
Resolution |
kolors-v1-5 |
Face/subject reference |
Up to 2048x2048 |
kolors-v2-0 |
Image restyle |
Up to 2048x2048 |
kolors-v2-1 |
Text-to-image |
Up to 2048x2048 |
Specialty Models
| Feature |
Endpoint |
Model Versions |
| Lip Sync |
/v1/videos/lip-sync |
v1.6+ |
| Virtual Try-On |
/v1/images/kolors-virtual-try-on |
v1.5 |
| Video Extension |
/v1/videos/video-extend |
All video models |
| Effects |
/v1/videos/effects |
v1.6+ |
| Motion Control |
T2V/I2V with camera_control |
v1.6+ |
Mode Selection
Every video generation accepts a mode parameter:
| Mode |
Credits (5s) |
Credits (10s) |
Use Case |
standard |
10 |
20 |
Drafts, previews, iteration |
professional |
35 |
70 |
Final output, client delivery |
Model Selection Decision Tree
Need fastest generation?
→ kling-v2-5-turbo + standard mode
Need highest quality?
→ kling-v2-6 + professional mode
Need audio in the video?
→ kling-v2-6 with motion_has_audio: true
Image-to-video only?
→ kling-v2-1 (optimized for I2V)
Budget-conscious production?
→ kling-v2-5-turbo + standard mode (10 credits/5s)
Legacy compatibility?
→ kling-v1-6 (stable, well-documented)
API Usage
# Specify model in any video generation request
response = requests.post(f"{BASE}/videos/text2video", headers=headers, json={
"model_name": "kling-v2-6", # model version
"mode": "professional", # standard or professional
"prompt": "A futuristic city at sunset with flying cars",
"duration": "5",
"aspect_ratio": "16:9",
})
Aspect Ratios (All Models)
| Ratio |
Use Case |
16:9 |
Landscape, YouTube, presentations |
9:16 |
Vertical, TikTok, Reels, Stories |
1:1 |
Square, Instagram, thumbnails |
4:3 |
Classic TV, presentations |
3:4 |
Portrait photos |
3:2 |
Standard photography |
2:3 |
Tall portrait |
21:9 |
Ultra-wide, cinematic |
Resources
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: jeremylongshore-claude-code-plugins-plus-skills-klingai-mode3description: Kling AI Model Catalog4---5# Kling AI Model Catalog67## Overview89Kling AI offers multiple model versions across video generation, image generation, lip sync, virtual try-on, and effects. Each version trades off quality, speed, and cost. This skill is the reference for choosing the right model.1011## Video Generation Models1213| Model ID | Supports | Max Duration | Resolution | Speed | Quality |14|----------|----------|-------------|------------|-------|---------|15| `kling-v1` | T2V, I2V | 10s | 720p | Fast | Good |16| `kling-v1-5` | I2V only | 10s | 1080p | Fast | Better |17| `kling-v1-6` | T2V, I2V | 10s | 1080p | Medium | Better+ |18| `kling-v2-master` | T2V, I2V | 10s | 1080p | Medium | High |19| `kling-v2-1` | I2V only | 10s | 1080p | Medium | High |20| `kling-v2-1-master` | T2V, I2V | 10s | 1080p | Medium | High |21| `kling-v2-5-turbo` | T2V, I2V | 10s | 1080p 30fps | Fast | High |22| `kling-v2-6` | T2V, I2V | 10s | 1080p 30-48fps | Medium | Highest |2324**T2V** = text-to-video, **I2V** = image-to-video2526### Kling v2.5 Turbo (Recommended for Speed)27- 40% faster than v2.028- Up to 1080p at 30 FPS29- Best cost/quality ratio for production pipelines3031### Kling v2.6 (Recommended for Quality)32- Native audio generation (voice, SFX, ambient in one pass)33- 1080p at 30-48 FPS34- Set `motion_has_audio: true` for synchronized audio3536## Image Generation Models (Kolors)3738| Model ID | Purpose | Resolution |39|----------|---------|------------|40| `kolors-v1-5` | Face/subject reference | Up to 2048x2048 |41| `kolors-v2-0` | Image restyle | Up to 2048x2048 |42| `kolors-v2-1` | Text-to-image | Up to 2048x2048 |4344## Specialty Models4546| Feature | Endpoint | Model Versions |47|---------|----------|----------------|48| **Lip Sync** | `/v1/videos/lip-sync` | v1.6+ |49| **Virtual Try-On** | `/v1/images/kolors-virtual-try-on` | v1.5 |50| **Video Extension** | `/v1/videos/video-extend` | All video models |51| **Effects** | `/v1/videos/effects` | v1.6+ |52| **Motion Control** | T2V/I2V with `camera_control` | v1.6+ |5354## Mode Selection5556Every video generation accepts a `mode` parameter:5758| Mode | Credits (5s) | Credits (10s) | Use Case |59|------|-------------|---------------|----------|60| `standard` | 10 | 20 | Drafts, previews, iteration |61| `professional` | 35 | 70 | Final output, client delivery |6263## Model Selection Decision Tree6465```66Need fastest generation?67 → kling-v2-5-turbo + standard mode6869Need highest quality?70 → kling-v2-6 + professional mode7172Need audio in the video?73 → kling-v2-6 with motion_has_audio: true7475Image-to-video only?76 → kling-v2-1 (optimized for I2V)7778Budget-conscious production?79 → kling-v2-5-turbo + standard mode (10 credits/5s)8081Legacy compatibility?82 → kling-v1-6 (stable, well-documented)83```8485## API Usage8687```python88# Specify model in any video generation request89response = requests.post(f"{BASE}/videos/text2video", headers=headers, json={90 "model_name": "kling-v2-6", # model version91 "mode": "professional", # standard or professional92 "prompt": "A futuristic city at sunset with flying cars",93 "duration": "5",94 "aspect_ratio": "16:9",95})96```9798## Aspect Ratios (All Models)99100| Ratio | Use Case |101|-------|----------|102| `16:9` | Landscape, YouTube, presentations |103| `9:16` | Vertical, TikTok, Reels, Stories |104| `1:1` | Square, Instagram, thumbnails |105| `4:3` | Classic TV, presentations |106| `3:4` | Portrait photos |107| `3:2` | Standard photography |108| `2:3` | Tall portrait |109| `21:9` | Ultra-wide, cinematic |110111## Resources112113- [Model Documentation](https://app.klingai.com/global/dev/document-api/apiReference/model/skillsMap)114- [Video Duration Reference](https://app.klingai.com/global/dev/document-api/apiReference/model/videoDuration)115- [Pricing](https://app.klingai.com/global/dev/document-api/productBilling/prePaidResourcePackage)116117---118> Converted and distributed by [TomeVault](https://tomevault.io/claim/jeremylongshore) — claim your Tome and manage your conversions.119<!-- tomevault:4.0:skill_md:2026-04-11 -->