Previsualization Scene Plan
Plan blocking, environment, camera positions and action before a single frame is generated.
Produces a practical previs plan for one scene: a described floor plan, character blocking and movement paths, camera positions relative to that space, environment build and the action timeline everything hangs on.
Ready-to-use prompt
The prompt
Copy it as-is, then swap the bracketed placeholders for your own details before running it.
Role: You are a previsualization supervisor planning a scene before generation.
Context:
- Scene: {{scene}}
- Location and environment: {{location}}
- Characters and their objectives: {{characters}}
- Runtime: {{runtime}}
Task: Produce a previs plan containing:
1. Floor plan in words - the space, its boundaries, entrances and key furniture or terrain
2. Blocking - starting position, movement path and ending position for each character
3. Camera positions plotted against that floor plan, numbered, with what each sees
4. Environment build - light sources and direction, atmosphere, background activity
5. Action timeline - what happens second by second across the runtime
6. Production risks - what will be hardest to generate convincingly and the fallback
Rules:
- Camera positions must be described relative to the floor plan, not in isolation.
- Every character must have a stated start and end position, even if static.
- Light sources must be physical and named, not adjectives.
- Do not write generation prompts or shot descriptions here.
Output: the plan in the six sections above, then the three highest production risks.Estimated results
Editor's note
Why this prompt matters
Storyboards show frames; previs shows the space those frames are taken in. Without it, shot three puts the door on the wrong wall and the sequence quietly stops making sense. This plan builds the room first - boundaries, furniture, light sources - then places people and cameras inside it, so every later shot has a consistent world to be photographed from.
Anatomy
Prompt engineering breakdown
Role
Context
Goal
Constraints
Output format
What you'll get
Expected output
A described floor plan, per-character blocking with start and end positions and movement paths, numbered camera positions with their coverage, an environment and lighting build, a second-by-second action timeline and the three biggest production risks with fallbacks.
Under the hood
Why this prompt works
Anchoring camera positions to a described floor plan is what keeps geography consistent once clips are generated independently. Requiring named physical light sources instead of mood adjectives is what makes lighting reproducible from shot to shot rather than reinvented each time.
Model fit
Best AI models for this prompt
Claude
Best at holding spatial logic and catching contradictions in blocking.
ChatGPT
Fast at the action timeline and risk list.
Gemini
Strong when you paste a location photo and want the plan built around the real space.
When to use
- Before boarding a complex scene with movement and multiple characters.
- When shots keep contradicting each other about the space.
- When briefing collaborators on a scene they will generate separately.
When not to use
- For a single static shot.
- For the story structure of a whole video - use the beat sheet.
- For converting shots into model prompts.
Get more from it
Pro tips
- 1
Write the floor plan first and refer back to it constantly.
- 2
Give every character an end position, even a static one.
- 3
Name light sources physically so shots can repeat them.
- 4
Use the risk list to decide what to test-generate first.
Don't ship this
Common mistakes
✗ Planning cameras without a described space.
Fix — Build the floor plan first and place cameras against it.
✗ Using mood words instead of light sources.
Fix — Name the window, lamp or fire and its direction.
✗ Covering several locations in one plan.
Fix — One plan per scene and location.
People also ask
Frequently asked questions
Q.Do I need previs for a short social video?
Rarely. It pays off when characters move through a space or several shots must agree on geography.
Q.How is this different from a shot list?
A shot list enumerates shots. Previs describes the space, blocking and timing those shots are taken from, so the list can be built without contradictions.
Q.Can I use a real location?
Yes. Paste photos or a description as the location input and the plan is built around the actual space.