Notes by ReelStack · AI-assistedUpdated 29 September 2026

You're Not Behind (Yet): How to Start Making AI Videos in 14 Minutes

Provides actionable prompting frameworks for timestamped shot sequencing and illustrates how to preserve skin textures and character identity using image-to-video workflows.

Video thumbnail: You're Not Behind (Yet): How to Start Making AI Videos in 14 Minutes
Original YouTube video

Youri van Hofwegen

Published

Watch the original video ↗

What this lesson covers

Youri van Hofwegen breaks down practical AI video production workflows utilizing Higgsfield and Seedance 2.5. He covers timestamped text-to-video prompting, native audio generation, image-to-video start framing, and character reference sheets to ensure visual consistency.

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. 02:07 ↗

    Structuring text prompts into explicit timestamp intervals creates cohesive shot progression with a defined beginning, middle, and end in continuous generations.

  2. 03:45 ↗

    Native audio generation within video models such as Seedance 2.5 adds significant perceived tension and realism compared to silent visual-only renders.

  3. 04:25 ↗

    Generating a dedicated starting frame first locks composition and lighting parameters before prompting camera movement.

  4. 06:58 ↗

    Texture descriptions (such as visible skin pores and natural asymmetry) must be carried over from image generation prompts into video prompts to prevent the model from smoothing them out.

  5. 08:18 ↗

    Referencing specific photographic styles, like sports photojournalism with defined focal lengths, prevents generative models from defaulting to artificial or video game aesthetics.

Workflow outlined in the video

  1. Structure text-to-video prompts using timed action breakdowns to direct multi-phase motion inside a single unbroken generation.
  2. Select Seedance 2.5 in Higgsfield to generate synchronized video and environmental audio in a single pass.
  3. Generate a 2K initial image using a model like Nano Banana Pro to lock framing, lighting, and composition prior to video animation.
  4. Create a dedicated character reference sheet showing full-body and frontal facial angles to maintain subject identity across scenes.
  5. Maintain granular photographic and texture prompt descriptors across both the image creation and video generation stages.

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

14,028 views captured 29 September 2026. ReelStack recommendation score: 51/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Show the calculation
  • 65% performance: 0.75× views vs 12 other channel videos observed at a similar age. View-evidence factor 93% (views / (views + 1,000))
  • 25% freshness: 96/100 with a 14-day half-life
  • Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
  • 10% engagement: 8/100; 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.