Nano Banana Pro Prompt Builder V1 [User Guide]: Setup & Cinematic Angles Workflow
Provides a reproducible workflow that lets AI filmmakers produce consistent multi‑shot sequences without a physical crew.
What this lesson covers
A step‑by‑step guide walks through installing Nano Banana Pro Builder, connecting a Google AI Studio API key, and using the UI to craft detailed prompts for multi‑angle, cinematic AI sequences. It demonstrates shot‑type selection, lighting, film stock, lens choices, and exporting prompts for downstream video generators.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 00:04 ↗
Installation is a single click; the app launches directly to the dashboard.
- 01:24 ↗
Input subject, action, and environment to auto‑populate the prompt skeleton.
- 02:09 ↗
Choose shot type (e.g., over‑the‑shoulder) to embed camera angle into the prompt.
- 03:00 ↗
Select film stock, lens focal length, and anamorphic settings for authentic cinematic texture.
- 04:02 ↗
The “Generate Multiple Angles” button creates four varied shots while preserving character details.
- 06:20 ↗
Export prompts or JSON to Gemini, Cling, Runway, or Google VO 3.1 for final video assembly.
Workflow outlined in the video
- Download Nano Banana Pro Builder and run the installer.
- Create a Google AI Studio API key and paste it into the app’s Connect API section.
- Enter a concise description of subject, action, and environment.
- Pick a shot type and camera angle that matches your storyboard.
- Configure camera gear, lens type, film stock, lighting source, and aspect ratio.
- Generate the primary image, then click “Generate Multiple Angles” for additional perspectives.
- Copy the resulting prompt or JSON to your chosen image/video generator and assemble the sequence.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
14,597 views captured 23 October 2026. ReelStack recommendation score: 34/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.63× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 94% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 100/100; likes + 4× comments, smoothed with a 500-view neutral prior