klingai-model-catalog
A reference guide to Kling AI model versions, detailing supported features, performance benchmarks, and use cases.
Install
mkdir -p .claude/skills/klingai-model-catalog && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8653" && unzip -o skill.zip -d .claude/skills/klingai-model-catalog && rm skill.zipInstalls to .claude/skills/klingai-model-catalog
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Explore Kling AI models, versions, and capabilities for video and imageKey capabilities
- →Compare video generation models by speed and quality
- →Identify models supporting text-to-video or image-to-video
- →Select models based on production requirements
- →Explore specialty features like lip sync and virtual try-on
- →Determine appropriate aspect ratios for different platforms
How it works
The catalog maps model IDs to specific capabilities, performance metrics, and cost tiers to guide selection based on project needs.
Inputs & outputs
When to use klingai-model-catalog
- →Selecting models by project requirement
- →Comparing model speed and quality
- →Checking feature support
- →Optimizing for production speed or quality
About this skill
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: truefor 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
When not to use it
- →Using legacy models for new production pipelines
- →Selecting high-cost professional modes for draft iterations
Limitations
- →Model availability varies by feature set
- →Professional mode incurs higher credit costs
How it compares
This provides a structured decision guide for model selection rather than testing models by trial and error.
Compared to similar skills
klingai-model-catalog side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| klingai-model-catalog (this skill) | 0 | 27d | Review | Beginner |
| jupyter-notebook | 30 | 6mo | Review | Intermediate |
| juicebox-core-workflow-b | 1 | 27d | Review | Advanced |
| obspy-data-api | 1 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
jupyter-notebook
davila7
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
juicebox-core-workflow-b
jeremylongshore
Implement Juicebox candidate enrichment workflow. Use when enriching profile data, gathering additional candidate details, or building comprehensive candidate profiles. Trigger with phrases like "juicebox enrich profile", "juicebox candidate details", "enrich candidate data", "juicebox profile enrichment".
obspy-data-api
benchflow-ai
An overview of the core data API of ObsPy, a Python framework for processing seismological data. It is useful for parsing common seismological file formats, or manipulating custom data into standard objects for downstream use cases such as ObsPy's signal processing routines or SeisBench's modeling API.
perplexity-core-workflow-b
jeremylongshore
Execute Perplexity secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like "perplexity secondary workflow", "secondary task with perplexity".
source-coding
parcadei
Problem-solving strategies for source coding in information theory
biopython
davila7
Primary Python toolkit for molecular biology. Preferred for Python-based PubMed/NCBI queries (Bio.Entrez), sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), advanced BLAST workflows, structures, phylogenetics. For quick BLAST, use gget. For direct REST API, use pubmed-database.