# Kling 2.x — Video Model Knowledge

## Provider
Kuaishou (China)

## Type
Diffusion

## Strengths

- **Realistic human motion** (best in class for walking, gesturing)
- **Lip sync** is strongest among AI video models
- More complex motion supported than Veo
- Cinematic look with proper prompting
- 10-second clips supported
- Good with Asian features (and others)
- Image-to-video conversion

## Weaknesses

- No audio dependency (must add audio in post)
- Long takes lose consistency
- Western faces sometimes "Asian-leaning"
- Verbose prompts confuse the model
- Documentation primarily Chinese

## Best Practices

1. **Structured key-value format** — not natural language
2. Maximum 80-100 words (much shorter than Veo)
3. Cinematic style MUST be explicitly stated
4. Aspect ratio and duration as parameters, not prompt text
5. Image input supported and recommended
6. Lip sync mode for dialogue scenes

## Prompt Anatomy

```
Subject: [description]
Action: [motion description]
Camera: [shot type, angle, movement]
Setting: [environment]
Lighting: [setup]
Style: [cinematic notes]
Duration: Ns
```

## Sample Prompt

```
Subject: 35-year-old man, charcoal wool coat, standing by window
Action: slow head turn from right to left, looks toward door, no body movement
Camera: medium shot, eye-level, completely static, no camera movement
Setting: 1960s diner interior at night, rain visible through window
Lighting: warm tungsten key from ceiling + cool blue window backlight
Style: cinematic, melancholic mood, shallow depth of field, photorealistic
Duration: 6s
```

## Lip Sync Mode

For dialogue clips, Kling has dedicated lip sync. Provide:
- Audio file (or text-to-speech reference)
- Subject framed for face visibility
- Static or minimal camera

```
Subject: woman, 30 years old, dark hair, professional attire
Action: speaking the dialogue, natural facial expression matching emotion
Camera: medium close-up, static, eye-level
Lip sync to: "I never expected to see you here." [tone: surprised, soft]
Duration: 5s
```

## Image-to-Video

### Mode A — Start frame only
Provide first frame as reference image:
```
[Reference image: starting frame]
Action: subject begins to walk forward, then stops
Camera: static medium shot
Duration: 5s
```

### Mode B — Start + End frame (key Kling 3.0 feature)
Kling 3.0 has **native start-and-end-frame** support. Provide TWO reference images, model generates the transition. The most powerful continuity tool — director-decided per shot (CLAUDE.md "Video prompt qaydaları" #3).

**Use Mode B when:**
- Emotional arc (exhaustion → smile, neutral → reaction)
- Specific action endpoint (hover → tap, closed → open)
- Pose evolution (standing → bent → straight)
- Continuity bridge between sequential clips

**Kling UI / API:**
- Upload `start_frame` (first image)
- Upload `end_frame` (last image)
- Prompt describes the transition

**Prompt format:**
```
Start frame: [reference image — initial state]
End frame: [reference image — final state]
Action: gradual transition from start state to end state — describe HOW (timing, micro-motions, expression evolution)
Camera: [shot type, angle, movement during transition]
Setting: [environment — constant across both frames]
Lighting: [setup — constant]
Style: [cinematic notes]
Duration: Ns (typically 3-6s for clean transitions)
```

**Sample Mode B prompt:**
```
Start frame: woman bent forward, hands on knees, exhausted, no expression
End frame: same woman, same pose, but with a small genuine smile, eyes lifting toward horizon
Action: 0-1s: heavy recovery breath, no expression change. 1-2s: subtle softening at corners of mouth. 2-3s: smile emerges gradually, eyes lift. 3-4s: final state held.
Camera: close-up, 85mm, hand-held respired, very slow push-in (10cm closer over duration)
Setting: pre-dawn park trail, warming light, mist still hanging
Lighting: warming pre-dawn ambient, faint horizon rim on cheekbone
Style: cinematic Wieden+Kennedy documentary, photorealistic, authentic smile (NOT posed)
Duration: 4s
Aspect: 9:16
```

**Mode B best practices:**
- **Start and end frames must share environment** — same location, similar lighting, same subject (different expression/pose OK)
- **Describe transition as time-segments** — "0-1s: ..., 1-2s: ..."
- **Subject identity must remain consistent** — Kling 3.0 handles this well if both frames are clearly the same person
- **Camera move can happen during transition** — slow push-in, drift, etc., but keep simple

## Aspect Ratios

- 16:9, 9:16, 1:1
- Set as parameter, not in prompt text

## Common Mistakes

- Verbose natural language prose
- Including audio cues (Kling doesn't generate audio)
- Multiple camera movements
- Multiple actions in sequence

## Pricing tier
$$$ — moderate-high

## Speed tier
Slow — 1-3 minutes per clip