Notes by ReelStack · AI-assistedUpdated 27 September 2026

The Cully Hill Boys | N3on, Israel Adesanya and MK | AI Action Film

This release marks a significant proof-of-concept for long-form AI feature production, offering filmmakers a fully transparent blueprinted project to study.

Video thumbnail: The Cully Hill Boys | N3on, Israel Adesanya and MK | AI Action Film
Original YouTube video

Higgsfield AI

Published

Watch the original video ↗

What this lesson covers

The Cully Hill Boys is a 110-minute feature-length AI film rendered on Higgsfield with Seedance 2.5, blending real digital talent with synthetic environments and scenes. The entire $2,000,000 project has been open-sourced, giving creators complete access to every prompt, character asset, and production detail.

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. 0:27 ↗

    Multi-character dialogue scenes can sustain coherent narrative pacing and spatial awareness over extended runtimes.

  2. 8:56 ↗

    Musical performances and lip-synced rap scenes can be visually anchored using targeted prompt setups and model generation.

  3. 12:12 ↗

    Open-sourcing full feature productions provides valuable prompt engineering patterns for long-form visual consistency.

Workflow outlined in the video

  1. Navigate to the open-sourced project page on Higgsfield to inspect the scene-by-scene prompt structure for feature films.
  2. Analyze how digital cast performances were blended into AI-generated backgrounds and dynamic lighting setups.
  3. Study the narrative asset organization to learn how consistent character looks were maintained across 110 minutes.
  4. Replicate and adapt specific prompt parameters in Seedance 2.5 to experiment with high-budget scene layouts.

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

191,325 views captured 27 September 2026. ReelStack recommendation score: 47/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Show the calculation
  • 45% performance: 1.53× views vs 9 other channel videos observed at a similar age. View-evidence factor 99% (views / (views + 1,000))
  • 25% freshness: 9/100 with a 14-day half-life
  • 20% momentum: 648 views/day vs 522 channel baseline (9 comparable uploads), with the same view-evidence factor
  • 10% engagement: 69/100; 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.