How to Make 2D Animation Videos With AI (No Experience)
This tutorial shows how multi-model workflows combining script generation, style reference boards, and character sheets can bypass traditional animation bottlenecks for indie creators.
What this lesson covers
Youri van Hofwegen demonstrates a 15-minute workflow for producing 2D animated shorts using Higgsfield, Claude, and Seedance. The process covers moodboarding reference styles, structuring detailed scene breakdowns with an AI chatbot, and maintaining character and location consistency across generations.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:16 ↗
Collect three to five strong reference images of your desired animation style to build a style reference mood board.
- 1:35 ↗
Use a structured prompt in Claude to break your story concept into a 3-part sequence with clear visual descriptions.
- 3:47 ↗
Generate a character sheet with front, back, and close-up views to maintain character consistency across multiple AI generations.
- 5:13 ↗
Create separate reference assets for locations and recurring objects to ensure visual continuity throughout the video.
Workflow outlined in the video
- Gather 3-5 reference images matching your target animation style.
- Upload the reference images into Higgsfield to generate a unified style mood board.
- Paste the story prompt into Claude along with your core concept to generate a structured 3-part narrative breakdown.
- Generate a consistent character sheet showing multiple angles using your reference mood board and base image.
- Create and save distinct location and asset reference images for your scenes.
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
126,893 views captured 25 October 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
- 45% performance: 3.53× views vs 14 other channel videos observed at a similar age. View-evidence factor 99% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 850 views/day vs 246 channel baseline (7 comparable uploads), with the same view-evidence factor
- 10% engagement: 1/100; likes + 4× comments, smoothed with a 500-view neutral prior