How I Built a $100K-Style Car Commercial Using Weavy AI (Full Workflow)
A modular, credit‑efficient pipeline empowers AI filmmakers to produce high‑quality commercial content at scale.
What this lesson covers
Diego walks through a Weavy AI workflow that generates multi‑angle car commercial shots using structured prompts, Nano Banana image generation, and Higgsfield video rendering. The process automates shot planning, reduces credit spend, and creates a reusable template for future client work.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 00:54 ↗
The workflow is split into three blocks: prompt creation, multi‑angle image generation, and video rendering in Higgsfield.
- 02:56 ↗
Using Nano Banana (or Nano Banana 2) to generate five camera angles per scene ensures comprehensive coverage for the final video.
- 04:56 ↗
Running all image nodes together costs 136 credits, highlighting the importance of batch processing for cost efficiency.
- 06:14 ↗
Providing reference images prevents AI hallucinations, keeping the car’s design accurate across all angles.
- 07:38 ↗
The completed template can be reused for new projects by swapping the source car files, dramatically cutting setup time.
Workflow outlined in the video
- Write a detailed system prompt describing the desired scenes and required camera angles.
- In Weavy, set up an array node to list the five shot types (macro, close‑up, medium, medium‑wide, wide).
- Feed each shot instruction into a Nano Banana image node, attaching reference images to guide the AI.
- Batch‑run the image nodes, note the credit usage, then export the generated images.
- Import the images into Higgsfield, select a video generation model, and render the final video clips.
- Save the entire node setup as a template to reuse for future commercial projects.
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
5,793 views captured 22 October 2026. ReelStack recommendation score: 33/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.89× views vs 4 other channel videos observed at a similar age. View-evidence factor 85% (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: 69/100; likes + 4× comments, smoothed with a 500-view neutral prior