Notes by ReelStack · AI-assistedUpdated 26 September 2026

Stop Stealing Movie Scenes with AI. Do This Instead. (Claude skills for better prompting)

Shows filmmakers how to bypass tedious text prompting for complex camera and character movement by using real video reference plates and specialized Claude prompt skills.

Video thumbnail: Stop Stealing Movie Scenes with AI. Do This Instead. (Claude skills for better prompting)
Original YouTube video

JOEY

Published

Watch the original video ↗

What this lesson covers

Joey breaks down how to use Higgsfield's Genjutsu feature combined with a custom Claude skill called Motiondojo to transfer camera and character motion from live-action reference footage into consistent AI scenes. He cautions against ripping copyrighted movie scenes and instead demonstrates filming original motion references to drive complex shot choreography.

Key takeaways from the creator

AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.

  1. 04:19 ↗

    Genjutsu allows creators to use live video reference to drive full cinema camera and character motion while maintaining character consistency with image references.

  2. 04:55 ↗

    Relying on motion reference videos eliminates the need to burn credits repeatedly trying to prompt complex camera and character choreography via text.

  3. 05:28 ↗

    Custom Claude skills (like Motiondojo) can break down reference screenshots, assets, and target scene modifications to prompt Genjutsu accurately.

  4. 06:12 ↗

    Attempting to swap complex objects (like turning an airplane into a dragon) can push motion-transfer models past their limits if the geometry and action diverge too heavily.

  5. 07:43 ↗

    Sourcing original reference video by acting out scenes with practical props and phone cameras produces cleaner custom AI shots than ripping movie scenes.

Workflow outlined in the video

  1. Record original live-action reference footage capturing the exact camera motion and body choreography you want.
  2. Take screenshot frames from your reference video alongside your character and environment reference plates.
  3. Load the reference images into Claude using a dedicated prompting skill (such as Motiondojo).
  4. Specify whether the tool should transfer camera movement, character motion, or both, detailing what objects and environments to swap.
  5. Feed the generated prompt and video reference into Higgsfield's Genjutsu tool to generate the final cinematic shot.

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

20,683 views captured 26 September 2026. ReelStack recommendation score: 60/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Show the calculation
  • 65% performance: 0.88× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 95% (views / (views + 1,000))
  • 25% freshness: 94/100 with a 14-day half-life
  • Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
  • 10% engagement: 75/100; likes + 4× comments, smoothed with a 500-view neutral prior

Read our methodology and limitations →

Powered by ReelStack

Help keep this running

Your tip funds servers, models, and the time it takes to ship new tools faster. Set any amount below — every bit helps.