muapi-ugc-video-factory

Generates vertical 9:16 UGC video ads from person and product photos using MuAPI models.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating UGC-style video ads normally requires filming a real person with a product, which is slow and expensive. This Skill turns a person photo, a product photo, and an optional spoken script into a 10-second vertical 9:16 video ad with native dialogue audio.

Core Features & Use Cases

  • Three-Stage Pipeline: GPT writes a director-grade photography prompt, Nano-Banana Pro Edit fuses the person and product into a hero image, and Seedance 2.0 VIP animates it into a talking video.
  • Native Audio Dialogue: The on-screen person speaks your custom script with synced audio in a natural, conversational tone.
  • Use Case: An e-commerce marketer uploads a model photo and a hat product shot, provides a one-sentence script, and receives a TikTok-ready UGC ad without any filming.

Quick Start

Ask the agent to create a UGC video ad from your person photo and product photo with your spoken script, and it will run the three-stage pipeline and deliver the finished 9:16 video.

Frequently Asked Questions about muapi-ugc-video-factory

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

FAQPage Schema
How do I create a UGC video ad from product photos?

Provide a person photo, a product photo, and an optional script. The pipeline generates a lifestyle hero image with Nano-Banana Pro Edit, then animates it into a 10-second vertical video with spoken audio using Seedance 2.0 VIP image-to-video.

What inputs does the UGC video factory require?

It requires two image URLs: a person photo (face and upper body work best) and a clear product photo with legible logo or text. The script and environment description are optional and have sensible defaults.

Can I use local image files with the muapi CLI?

Yes, upload local files first with 'muapi upload file <path> --output-json --jq .url' to get a hosted URL. The resulting URL is then passed as the person or product input to the pipeline.

What video formats and durations does Seedance 2.0 VIP support?

The VIP tier supports 9:16 vertical aspect ratio with durations from 4 to 15 seconds; 10 seconds is recommended for a one-to-two sentence script. Longer scripts get compressed and words may be clipped.

Why is my UGC video script getting cut off?

Seedance 2.0 compresses longer scripts and clips words when the dialogue exceeds the video duration. Keep the script to one or two short sentences that fit comfortably within 10 seconds.

Can I make multi-shot video ads with this pipeline?

Seedance VIP does not support multi-image image-to-video at 9:16 with audio. Instead, generate several hero image variations in Step 2 and animate each one independently, then edit the clips together.