Kling 1.6 Video Prompt: underwater coral reef teeming with tropical fish (Blade Runner 2049 atmospheric)

You are crafting a single production-ready Kling 1.6 video prompt. Output the prompt ONLY — no preamble, no explanation.

## Scene Parameters
- **Subject:** underwater coral reef teeming with tropical fish
- **Style:** Blade Runner 2049 atmospheric
- **Shot type:** medium shot
- **Camera motion:** gimbal smooth follow
- **Duration:** 20 seconds
- **Aspect ratio:** 16:9 widescreen
- **Lighting:** low-key dramatic Rembrandt

## Prompt Construction Rules
Follow this exact ordering for maximum fidelity on Kling 1.6:

1. **Lead with subject action in present tense.** Do not start with "A..." or "There is..." — start with the subject doing the verb.
2. **Environment and context.** One concrete sentence locating the subject in space.
3. **Camera behavior.** Name the lens (18mm / 35mm / 85mm / macro), the motion (gimbal smooth follow), and the framing (medium shot).
4. **Lighting and atmosphere.** Specify source direction, color temperature, and any haze/fog/particles.
5. **Style keywords optimized for Kling 1.6.** See model-specific tips below.
6. **Technical footer.** Resolution, frame rate if supported, aspect ratio (16:9 widescreen), duration (20 seconds).

## Tone and Word Choice
- Cinematic, concrete, no hedging adjectives.
- Use specific visual nouns, not abstract feelings. "Rain-slicked asphalt reflecting neon signage" beats "a cool rainy mood".
- Target 80-140 words in the final prompt. Dense but not padded.

## Model-Specific Quirks
- **Sora / Sora Turbo:** Avoids vague adjectives like "beautiful" or "amazing"; reward concrete physical descriptors. Strong at long takes, weak at complex text. Use comma-separated clauses, not lists.
- **Veo 3 / Veo 2:** Honors embedded audio prompts ("sound of waves crashing, distant seagulls"). Include a short audio line for Veo 3. Handles dialogue natively — wrap lines in quotes.
- **Runway Gen-3 Alpha:** Favors motion verbs ("glides", "sweeps", "pulls back") and explicit camera movement. Use their structured prompt format: [Camera Movement]: [Scene]: [Details].
- **Pika 2.0 / Pika 1.5:** Works best with shorter prompts (60-100 words) and benefits from "-ing" action verbs. Use /motion strength 2-4.
- **Kling 1.6 / Kling 1.5:** Loves cinematic references ("shot like a Christopher Nolan film"). Strong physics simulation — describe material interactions.
- **Hailuo / MiniMax:** Responds well to emotional tone words. Short and evocative beats long and precise.
- **Luma Dream Machine:** Keyframe-driven; describe the END state, not just the beginning. "...and ends with the camera craning up over the rooftops."
- **LTX Video / Lightricks LTX:** Fast but literal — be explicit about what should NOT change (background, subject identity).
- **Hunyuan Video:** Excellent with complex human motion; specify body part movements.
- **Mochi 1:** Open source; prefers positive-only prompts with explicit motion language.

## Pitfalls to Avoid
- Never use negatives ("no blur", "not dark") — most video models ignore negatives or invert them.
- Do not stack more than 2 subjects; multi-character consistency is unreliable under 10s.
- Avoid text rendering in Kling 1.6 unless it is Veo 3 or Kling 1.6.
- Do not specify more than one camera motion. "gimbal smooth follow" only.

## Example Output Block
Render the final prompt inside a single markdown code block like this:

```
[Your crafted Kling 1.6 prompt here — one continuous paragraph, 80-140 words]
```

After the code block, add a one-line note: "Suggested parameters: 16:9 widescreen, 20 seconds, and any Kling 1.6-specific flags."

Do not output anything else.