Lesson 4 of 5Beginner 13 min

How to start making AI videos (beginner to advanced)

Key takeaways

  • Planning beats prompt writing: storyboard your shots first
  • Reusable characters keep the same person consistent across shots
  • Custom locations and directed scenes make videos look intentional
  • A good plan saves generation credits

Now for making video from scratch with AI. Youri van Hofwegen, one of the best-known AI video creators on YouTube, shows his complete workflow for cinematic AI videos in 13 minutes, starting with a simple prompt and building up to properly directed scenes.

What it covers

He begins with the most basic approach, a single text prompt, and shows what you get. Then he levels up step by step: planning with storyboards, creating reusable characters so the same person looks consistent across shots, making custom locations, and finally directing full scenes with consistent results. At each stage he compares the output, so you can see what each extra step adds. His main lesson: planning matters more than clever prompt writing, and good planning also means using fewer generation credits.

Who it's for

Beginners who want to make AI videos that look intentional rather than random, for ads, social content, stories or product videos. No filming or editing experience needed.

Good to know

The workflow is shown in Higgsfield, and the video includes affiliate links and a bonus package. The planning approach (storyboard first, consistent characters, then scenes) works in other AI video tools too.

Tip: sketch your video as five to eight shots before you generate anything: who is in it, where, and what happens. Generating without a plan burns credits fast. Reuse the same character and location descriptions in every prompt for consistency. Once a shot works, save its exact prompt so you can recreate the style later.

Tools mentioned

Higgsfield logoHiggsfieldProprietaryFreemium

Higgsfield AI is a creative suite for generating images, videos, and voice content from text prompts or reference material. It offers tools for editing and upscaling media, plus an AI agent that automates creative workflows. The product is available on both web and mobile, and includes an MCP integration for use within Claude, along with an API for developers. It's aimed at creators, marketers, and teams who want to produce video, image, and audio content, including ads and cinematic scenes, without traditional production tools.