I Gave Claude $50 To Make an Al Commercial with SEEDANCE 2.0

What this lesson covers

Thomas Lundström executes a $50 challenge to produce a football-themed soda commercial within a strict 1-day timeline using Claude, Higgsfield MCP, and Seedance 2.0. By using voice dictation and custom Claude skills to orchestrate storyboard generation, character sheet creation, and canvas alignment, he establishes an efficient pre-production pipeline.

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. 01:23 ↗

   Integrating Higgsfield MCP into Claude allows creators to generate AI image storyboards directly within the chat interface using natural language.

2. 01:56 ↗

   Installing the storyboard cheat code skill into Claude optimizes prompt formatting for multi-frame storyboard layouts powered by Higgsfield MCP.

3. 03:18 ↗

   Using Wispr Flow voice dictation enables fast, detailed feedback loops and iteration on AI storyboard generation prompts without typing.

4. 04:31 ↗

   Requesting specific subset variations (like nine frames for a single action) at 2K resolution optimizes credit usage while building master storyboards.

5. 05:46 ↗

   Extracting character frames into character sheets inside Claude maintains character continuity across different story sequences.

6. 06:36 ↗

   Switching from GPT Image 2 to Nano Banana 2 resolves specific complex camera perspective prompts, such as extreme low-angle shots from inside a beverage can.

Workflow outlined in the video

1. Install Higgsfield MCP into your local environment and connect it to Claude.
2. Load the storyboard cheat code skill into Claude to enforce structured multi-shot prompt formats.
3. Dictate scene concepts into Claude using natural voice input to rapidly generate initial storyboard layouts.
4. Refine weak storyboard frames by requesting targeted multi-frame variations for specific scene actions.
5. Extract keyframe characters into reference sheets for consistent downstream generation in Seedance 2.0.
6. Assemble selected storyboard frames onto Higgsfield Canvas to finalize the full master layout prior to video synthesis.

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

3,465 views captured 24 October 2026. ReelStack recommendation score: 32/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Read our methodology and limitations →