muapi-storyboard-to-cooking-video

Generates a 15-second cinematic cooking tutorial video from a single person photo via a two-step reference-sheet and reference-to-video pipeline.

4.2k|481|Updated May 25, 2023
One-click install
npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-storyboard-to-cooking-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: muapi-storyboard-to-cooking-video
Source: https://github.com/SamurAIGPT/Generative-Media-Skills/tree/main/library/motion/storyboard-to-cooking-video
Command: npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-storyboard-to-cooking-video

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating a consistent, professional-looking cooking tutorial video from just one photo of a person is hard: faces drift between frames, kitchens change, and multi-step recipes lose continuity. This Skill solves that by first building a composite production reference sheet (character sheet, kitchen environment, and a 9-panel action board) and then animating the full sequence with dual image references so identity and setting stay locked.

Core Features & Use Cases

  • Composite Reference Sheet Generation: Uses gpt-image-v2-edit to produce a 3840x2160 board combining character views, kitchen location reference, and a 9-step action plan.
  • Dual-Reference Video Generation: Uses bytedance-seedance-2-0-reference-to-video-fast with the original photo as identity anchor and the reference sheet as narrative guide, including generated audio.
  • Configurable Output: Customize dish, kitchen style, outfit, duration (10-15s), aspect ratio (16:9 or 9:16 for Reels), and resolution (480p/720p).
  • Use Case: A food content creator uploads their photo and gets a polished 15-second pasta-making tutorial video with consistent face, outfit, and kitchen, ready to post or re-render vertically for Reels.

Quick Start

Ask the agent to turn your photo into a 15-second cooking tutorial video by providing the photo URL and optionally specifying the dish, kitchen style, and outfit.

Frequently Asked Questions about muapi-storyboard-to-cooking-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a photo into a cooking tutorial video?

Provide a URL of the person photo and optionally specify the dish, kitchen style, and outfit. The skill first generates a composite reference sheet with gpt-image-v2-edit, then animates the full cooking sequence with bytedance-seedance-2-0-reference-to-video-fast using both images as references.

How does the video keep the same face in every frame?

It uses a dual-reference approach: the original person photo locks identity while the generated reference sheet locks choreography and environment. Dropping either reference causes the face or kitchen consistency to fail.

Can I make a vertical cooking video for Instagram Reels?

Yes, set the aspect_ratio input to 9:16 for vertical output. The default is 16:9, and you can re-render the same person and dish in vertical format as a follow-up.

Does the generated cooking video include audio?

Yes, the seedance reference-to-video endpoint natively generates audio when generate_audio is true. The prompt includes audio direction for kitchen ambience and culinary sound effects; omitting it produces a random soundtrack.

What are the duration and resolution limits for the video?

Duration supports 10 or 15 seconds, with 15 seconds fitting the full 9-step arc and shorter durations collapsing to fewer beats. Resolution options are 480p and 720p, and sequences of 8 seconds or less should use only 5-6 action panels.