Introduction
Vision turns a text prompt into a 9-shot storyboard with consistent characters, lighting, and art direction across every frame. It's built for pre-production, locking your visual language before you start generating video.
How to get started
From the homepage, click Trends → See all → select Vision
Describe your scene and add any reference images
Vision generates a 3×3 storyboard grid
Storyboard options:
Boards - generates your storyboard sequence from the prompt
Looks - keeps your character's appearance consistent across every frame
Angles - shifts the camera perspective on any frame without losing character continuity
💡 Tips for better results | Why it helps |
Describe your character clearly in your first prompt | Vision uses this as the reference across all 9 shots |
Specify lighting and mood upfront | Vision carries this through the entire storyboard |
Use Angles after your initial generation | Gives you more control than describing every camera angle in the first prompt |
If a frame is almost right, extract it and use it as a reference image | Saves you from regenerating the whole storyboard from scratch |
Extracting a frame
Select any frame from your storyboard and extract it as a standalone image or send it directly into video generation to build out the scene.
