samuraigpt avatar

Muapi Ugc Video Factory

This is a three-stage pipeline for making TikTok-style product ads: you give it a photo of a person, a photo of your product, and a short script, and it spits out a 10-second vertical video where the person is holding or wearing the product and actually speaking your script out loud. It writes a photography prompt with GPT, composites the images with Nano-Banana Pro Edit, then animates everything with Seedance 2.0 VIP including synced audio. The VIP tier matters because it handles realistic faces without the restrictions of the Chinese models. Keep your script to one or two sentences or it'll get clipped. Good for quick UGC-style ad mockups without hiring talent or shooting footage.

skills.sh installs
1.8K
GitHub stars
4K
last updated
Aug 21, 2026

Install

$ npx -y skills add samuraigpt/generative-media-skills --skill muapi-ugc-video-factory --agent claude-code

Installs into .claude/skills of the current project.

Files

UGC Video Factory

Turn a person photo + product photo (+ optional script & environment) into a vertical 9:16 UGC-style video ad with native dialogue audio.

A three-stage pipeline:

  1. GPT writes a director-grade ultra-realistic lifestyle photography prompt from your inputs.
  2. Nano-Banana Pro Edit fuses the person + product into a single hero photo (1K, 9:16).
  3. Seedance 2.0 VIP Image-to-Video animates the hero photo into a 10s vertical UGC clip with synced spoken audio.

Inputs

Sponsors

Details

Repository
github.com/samuraigpt/generative-media-skills
Categories
Code Review & Quality, Automation & Workflows, Generative Media
First seen
Jul 14, 2026

More from samuraigpt/generative-media-skills

All 18
1giuseppe-trisciuoglio avatarralph-loopgiuseppe-trisciuoglio/developer-kitRalph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Pytho1.7Kskills.sh installs
2daymade avatarasr-transcribe-to-textdaymade/claude-code-skillsTranscribe audio/video to speaker-labeled text — who-said-what by default, plain-text opt-out; MLX-local on Apple Silicon or remote; local files, media URLs. Us1.7Kskills.sh installs
3everyinc avatarce-gemini-imagegeneveryinc/compound-engineering-pluginThis skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing 1.7Kskills.sh installs
4mims-harvard avatartooluniverse-sequence-retrievalmims-harvard/tooluniverseRetrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation. Quality hierarchy: RefSeq (NM_/NP_) > RefSeq predicted (XM_/XP_) > GenBank submissions1.7Kskills.sh installs
5pika-labs avatarfounder-product-videopika-labs/pika-pluginsUse when the user asks for founder product video or a task matching the examples below. Generate a 65-second founder-style product video from a product URL + us1.7Kskills.sh installs
6eronred avatarrating-prompt-strategyeronred/aso-skillsWhen the user wants to improve their app's star rating, increase ratings volume, optimize when and how they prompt users for a review, or recover from a bad rat1.7Kskills.sh installs