How I Made a $1M Red Bull F1 Commercial With AI + Blender
Provides an actionable framework for generating commercial-grade AI video assets by decoupling prompt writing to LLMs, generating structured model sheets, and using specialized image models for distinct subjects.
What this lesson covers
Creator kaye.creatives demonstrates a full workflow for producing an AI-driven Red Bull Formula 1 spec commercial. The breakdown focuses on generating character and vehicle model sheets, structuring location prompts with optical rendering blocks, and utilizing multi-model pipelines.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 03:02 ↗
Establishing foundational asset and model sheets prior to video generation prevents character face drifting and object morphing across cuts.
- 04:16 ↗
Visual references gathered from moodboards can be analyzed by Claude Opus 5.5 to engineer optimized character sheet prompts without manual prompt writing.
- 05:23 ↗
Model selection should match subject type: Cream 5.0 Pro excels at human skin texture and facial features, while Cadream handles sharp vehicle geometry and high-contrast lighting.
- 07:44 ↗
Appending an optical block structure to location prompts instructs image models to render anamorphic lens distortion, organic film grain, and stadium lighting instead of flat rendering.
Workflow outlined in the video
- Collect moodboard references for character outfits, vehicles, and environment lighting from reference platforms.
- Input reference imagery and narrative concepts into Claude Opus 5.5 to output standardized model sheet prompts.
- Generate human character model sheets in Higgsfield Cinema Studio using Cream 5.0 Pro with selfie and styling references.
- Create vehicle and asset turnarounds in Cadream to ensure consistent structural details and livery.
- Formulate environment prompts incorporating an optical block descriptor in Soul Cinema to lock in cinematic lens and grain attributes.
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
Put the lesson in context
When to use Blender previsualization for AI video →How to interpret the numbers
26,225 views captured 27 September 2026. ReelStack recommendation score: 50/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.47× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 96% (views / (views + 1,000))
- 25% freshness: 97/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 54/100; likes + 4× comments, smoothed with a 500-view neutral prior