Prompt Tips
The quality of your AI-generated output depends on how you write your prompt. This is a quick-start — for the comprehensive framework with camera language and shot recipes, see Prompting for Video Editors in Academy.
Prompt Optimizer
Section titled “Prompt Optimizer”modelBridge includes a one-click prompt optimizer. Click the sparkle button below the prompt field, and an AI rewrites your description into a model-optimized prompt.
- Cost: approximately $0.01 per use (shown in hover tooltip)
- How it works: your prompt is sent to an LLM that rewrites it with better structure and specificity
- The button is disabled when the prompt field is empty
- Undo: the optimized prompt replaces your text — Cmd+Z to revert
The Core Rule
Section titled “The Core Rule”Write prompts like shot descriptions: subject + action + environment + style + camera. 15–40 words. Specific and short beats long and vague every time.
| Instead of… | Try… |
|---|---|
| ”A city at night" | "Slow aerial dolly forward over a city skyline at night, neon lights reflecting in wet streets, light rain" |
| "Ocean waves" | "Close-up of waves crashing on rocks in slow motion, spray catching golden sunset light" |
| "A person walking" | "A woman in a red coat walking through a rainy street, camera tracking left, shallow depth of field” |
Tips by Generation Type
Section titled “Tips by Generation Type”Image-to-Video: Focus on motion, not the image. The model already sees your image — describe what should move.
- Good: “Gentle wind blowing through hair, subtle head turn to the left, soft smile”
- Less effective: “A portrait of a woman with brown hair”
Text-to-Speech: Use punctuation to control pacing. Commas for pauses, ellipses for dramatic effect. For ElevenLabs v3, use emotion tags like [excited], [whispers], [laughs].
Sound Effects: Describe with specificity. “Thunder rumbling in the distance, followed by heavy rain on a tin roof” — not “storm sounds.”
Prompt Persistence
Section titled “Prompt Persistence”Your prompt text carries over when you switch models. Write a prompt, switch from Kling v2.5 to Kling v3 Pro, and the text is already there. Model-specific settings reset to defaults, but your prompt stays.
Iterating on Results
Section titled “Iterating on Results”- Adjust the prompt — add more specific details about what was wrong
- Try the optimizer — it may restructure your prompt more effectively
- Switch models — different models interpret prompts differently
- Adjust parameters — sometimes changing duration, resolution, or aspect ratio helps more than changing the prompt
Go Deeper
Section titled “Go Deeper”- Prompting for Video Editors — full framework with camera terms, shot recipe, and common mistakes
- Negative Prompts — tell the AI what to avoid