Understanding Storyboards
Before generating any video images or audio, ADD CREATE first creates a storyboard — a structured, slide-by-slide plan for the video. Think of it as the AI sketching out the script and visual ideas for each slide before any assets are produced.
Storyboards are authored in English even when the final video will be rendered in another language. This keeps review, editing, and approval on a single source version before narration is synthesised.
What a Storyboard Contains
Section titled “What a Storyboard Contains”Each slide in the storyboard has two components:
- A narration line — what will be spoken aloud for that slide.
- A visual description — a description of the image to be generated for that slide, shaped by the visual style you chose.
The storyboard is generated automatically from your project’s documents and cannot be manually edited before the video is produced.
How Storyboards are Built
Section titled “How Storyboards are Built”When you launch a Video job, the platform:
- Searches your project’s documents for the most relevant content.
- Uses that content to plan a structured video with a logical flow — one slide per key point or topic.
- For each slide, writes the narration and composes a visual description appropriate to the chosen style.
- Generates all slide images and narration audio simultaneously before assembling the final video.
Video Formats
Section titled “Video Formats”| Format | Description |
|---|---|
| Explainer | A structured video covering the highlights of your documents in full |
| Brief | A shorter, high-level summary video |
Visual Styles
Section titled “Visual Styles”The visual style you select shapes the look of every generated image in the video:
| Style | Description |
|---|---|
| Classic | Clean, professional corporate look |
| Dark | Dark backgrounds with high contrast and a premium feel |
| Whiteboard | Hand-drawn illustration and sketch aesthetic |
| Neon | Vibrant neon colours and a tech-forward aesthetic |
| Watercolor | Soft, painterly watercolor art style |
Final Render Language
Section titled “Final Render Language”When you finalize a storyboard into a video, the render panel now includes a Final Render Language selector.
- The storyboard text and slide planning stay in English.
- The final narration and caption output use the selected render language.
- The selector exposes the full supported language list available for the render workflow.
Advanced Usage Notes
Section titled “Advanced Usage Notes”Use these patterns to get more predictable results:
- Keep inputs specific and scoped to one intent per generation request.
- Save intermediate outputs often, especially before running major edits or regenerations.
- Use review and assignment workflows early to reduce rework late in the lifecycle.
Troubleshooting
Section titled “Troubleshooting”If results are not what you expected:
- Verify source quality first (missing context, inconsistent structure, or conflicting inputs reduce output quality).
- Re-check selected options and audience/profile settings before re-running.
- If a job fails repeatedly, wait briefly and retry once; then escalate with the artifact or job context.
Frequently Asked Questions
Section titled “Frequently Asked Questions”Why did quality change between runs?
Section titled “Why did quality change between runs?”Different input context, settings, and model/runtime conditions can produce different outputs.
Should I regenerate or manually edit?
Section titled “Should I regenerate or manually edit?”Regenerate when the core structure is wrong; manually edit when only wording, ordering, or style needs adjustment.
What is the best way to reduce iteration cycles?
Section titled “What is the best way to reduce iteration cycles?”Start with clear scope, run smaller batches, and use review checkpoints after each major step.