AI Prompt for Video Generation (Sora, Veo, Runway)
Ready-to-paste Pika 1.5 prompt for a 30 seconds dolly zoom of viking longship battling a storm at sea rendered in vintage VHS 1990s with FPV swooping camera.
More prompts for Video Generation (Sora, Veo, Runway).
An image-to-video prompt for Luma Dream Machine that animates child jumping in rain puddles using slow push-in over 15 seconds while preserving identity.
A multi-shot cinematic breakdown prompt that gives Lightricks LTX a full scene of coffee being poured into a ceramic cup in IMAX nature documentary with Instagram Reel intent.
An image-to-video prompt for Hailuo MiniMax that animates abandoned Victorian mansion using crane up over 15 seconds while preserving identity.
An image-to-video prompt for Kling 1.5 that animates lone tree on a windswept cliff using dolly right over 30 seconds while preserving identity.
Ready-to-paste Kling 1.6 prompt for a 5 seconds insert shot of underwater coral reef teeming with tropical fish rendered in hyperrealistic photorealism with gimbal smooth follow camera.
A multi-shot cinematic breakdown prompt that gives LTX Video a full scene of time-lapse of a blooming flower in cinematic 35mm film grain with game cinematic trailer intent.
You are crafting a single production-ready Pika 1.5 video prompt. Output the prompt ONLY — no preamble, no explanation.
## Scene Parameters
- **Subject:** viking longship battling a storm at sea
- **Style:** vintage VHS 1990s
- **Shot type:** dolly zoom
- **Camera motion:** FPV swooping
- **Duration:** 30 seconds
- **Aspect ratio:** 4:3 classic
- **Lighting:** harsh midday sun with sharp shadows
## Prompt Construction Rules
Follow this exact ordering for maximum fidelity on Pika 1.5:
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 (FPV swooping), and the framing (dolly zoom).
4. **Lighting and atmosphere.** Specify source direction, color temperature, and any haze/fog/particles.
5. **Style keywords optimized for Pika 1.5.** See model-specific tips below.
6. **Technical footer.** Resolution, frame rate if supported, aspect ratio (4:3 classic), duration (30 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 Pika 1.5 unless it is Veo 3 or Kling 1.6.
- Do not specify more than one camera motion. "FPV swooping" only.
## Example Output Block
Render the final prompt inside a single markdown code block like this:
```
[Your crafted Pika 1.5 prompt here — one continuous paragraph, 80-140 words]
```
After the code block, add a one-line note: "Suggested parameters: 4:3 classic, 30 seconds, and any Pika 1.5-specific flags."
Do not output anything else.Replace the bracketed placeholders with your own context before running the prompt:
[Camera Movement]— fill in your specific camera movement.[Scene]— fill in your specific scene.[Details]— fill in your specific details.