klingai-camera-control
Control camera movements in Kling AI video generation. Use when creating cinematic shots, pans, tilts, zooms, or dolly moves. Trigger with phrases like 'klingai camera', 'kling ai camera motion', 'klingai cinematic', 'klingai pan zoom'.
What this skill does
# Kling AI Camera Control
## Overview
Add controlled camera movements to text-to-video and image-to-video generation using the `camera_control` parameter. Supports pan, tilt, zoom, roll, and dolly. Available on v1.6+ models.
**Supports:** `POST /v1/videos/text2video` and `POST /v1/videos/image2video`
## Camera Control Parameters
```json
"camera_control": {
"type": "simple", # "simple" = one movement axis
"config": {
"horizontal": 0, # Pan: -10 (left) to 10 (right)
"vertical": 0, # Tilt: -10 (down) to 10 (up)
"zoom": 0, # Zoom: -10 (out) to 10 (in)
"roll": 0, # Roll: -10 (CCW) to 10 (CW)
"pan": 0, # Dolly: -10 (left) to 10 (right)
"tilt": 0, # Dolly: -10 (down) to 10 (up)
}
}
```
**Rule:** For `type: "simple"`, only ONE field in `config` can be non-zero.
## Cinematic Shot Examples
### Slow Pan Right
```python
response = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
"model_name": "kling-v2-6",
"prompt": "A medieval castle on a cliff at sunrise, fog in the valley below",
"duration": "5",
"mode": "professional",
"camera_control": {
"type": "simple",
"config": {"horizontal": 5, "vertical": 0, "zoom": 0, "roll": 0, "pan": 0, "tilt": 0}
},
})
```
### Dramatic Zoom In
```python
response = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
"model_name": "kling-v2-6",
"prompt": "Close-up of a tiger's face, intense eyes, jungle background",
"duration": "5",
"mode": "professional",
"camera_control": {
"type": "simple",
"config": {"horizontal": 0, "vertical": 0, "zoom": 7, "roll": 0, "pan": 0, "tilt": 0}
},
})
```
### Tilt Up Reveal
```python
response = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
"model_name": "kling-v2-6",
"prompt": "A skyscraper, starting from the base looking up, glass and steel",
"duration": "5",
"mode": "standard",
"camera_control": {
"type": "simple",
"config": {"horizontal": 0, "vertical": 8, "zoom": 0, "roll": 0, "pan": 0, "tilt": 0}
},
})
```
### Dolly Forward
```python
response = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
"model_name": "kling-v2-master",
"prompt": "Walking through a dark forest, trees on both sides, moonlight filtering through",
"duration": "5",
"mode": "standard",
"camera_control": {
"type": "simple",
"config": {"horizontal": 0, "vertical": 0, "zoom": 0, "roll": 0, "pan": 0, "tilt": 5}
},
})
```
## Camera Control with Image-to-Video
```python
# Animate a landscape photo with a slow zoom out
response = requests.post(f"{BASE}/videos/image2video", headers=get_headers(), json={
"model_name": "kling-v2-1",
"image": "https://example.com/landscape.jpg",
"prompt": "Gentle wind, clouds moving slowly",
"duration": "5",
"camera_control": {
"type": "simple",
"config": {"horizontal": 0, "vertical": 0, "zoom": -5, "roll": 0, "pan": 0, "tilt": 0}
},
})
```
**Important:** For image-to-video, `camera_control` is mutually exclusive with `image_tail`, `dynamic_masks`, and `static_mask`.
## Shot Type Quick Reference
| Shot Type | Config Field | Value | Description |
|-----------|-------------|-------|-------------|
| Pan right | `horizontal` | 5-8 | Slow pan, good for landscapes |
| Pan left | `horizontal` | -5 to -8 | Reveal from right to left |
| Tilt up | `vertical` | 5-8 | Upward reveal (buildings, trees) |
| Tilt down | `vertical` | -5 to -8 | Downward motion |
| Zoom in | `zoom` | 5-10 | Focus on subject, dramatic |
| Zoom out | `zoom` | -5 to -10 | Reveal, establishing shot |
| Dutch tilt | `roll` | 3-5 | Unsettling, artistic angle |
| Push in | `tilt` | 3-5 | Dolly forward (depth effect) |
| Pull back | `tilt` | -3 to -5 | Dolly backward (reveal) |
## Intensity Guidelines
| Value Range | Effect |
|-------------|--------|
| 1-3 | Subtle, barely perceptible |
| 4-6 | Moderate, natural-feeling |
| 7-8 | Strong, dramatic |
| 9-10 | Maximum, may feel unnatural |
**Recommendation:** Start at 4-6 for most cinematic shots. Go higher for dramatic reveals or action sequences.
## Error Handling
| Error | Cause | Fix |
|-------|-------|-----|
| `400` invalid camera config | Multiple non-zero values in simple mode | Set only one field to non-zero |
| Jerky motion | Value too high | Reduce to 4-6 range |
| No visible movement | Value too low (1-2) | Increase to 3+ |
| Mutual exclusivity error | Combined with masks/image_tail | Use only camera_control OR masks |
## Resources
- [Camera Control Guide](https://app.klingai.com/global/quickstart/ai-camera-control-guide)
- [Motion Control Guide](https://app.klingai.com/global/quickstart/motion-control-user-guide)
- [Developer Portal](https://app.klingai.com/global/dev)
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.