pyang5166 GitHub avatar

gbro-collage-broll

pyang5166

gbro-collage-broll generates premium halftone paper-collage B-roll clips from short voiceover text, using a three-gate approval workflow and Gemini Omni Flash for video generation.

Stars

229

7-day growth

No data

Forks

21

Open issues

1

License

MIT

Last updated

2026-07-15

Why it is worth attention

It enforces a three-stage human approval process (concept → still frame → video) to prevent wasted API costs, while producing a distinctive stop-motion paper collage aesthetic.

Who it is for

  • Video editors seeking unique B-roll assets
  • Content creators who need to quickly visualize spoken lines
  • AI video workflow adopters wanting cost-efficient generation
  • Media producers requiring batch processing of short scripts

Use cases

  • Generating editorial-style B-roll for podcast or voiceover videos
  • Producing multiple collage animations from a list of script lines in one batch
  • Creating visually striking transitions or background clips for presentations

Strengths

  • Three-gate workflow minimizes expensive video re-generation by catching poor ideas early
  • Uses Gemini Omni Flash for first/last frame animation, ensuring consistent motion
  • Produces a unique halftone paper-collage look with flat color fields and stop-motion feel
  • Supports batch processing with partial pass-through for approved entries only

Considerations

  • Requires manual environment setup (Gemini API key, Python, ffmpeg) and dependencies
  • First frame may show slight paper edge details, potentially needing timeline tools for strict empty-field shots
  • Default locked to gemini-omni-flash-preview model; switching requires explicit specification

README quick start

安装

Description

半调纸拼贴 B-roll 生成 skill:三闸门审批,Gemini Omni Flash 首尾帧组装动画 | Editorial halftone paper-collage B-roll agent skill

Related repositories

Similar projects matched by category, topics, and programming language.

Robbyant
Robbyant GitHub avatar

lingbot-video

LingBot-Video is the first open-source large-scale Mixture-of-Experts (MoE) video generation model designed for embodied intelligence, offering efficient inference and state-of-the-art performance on robotics-related benchmarks.

Python
806
oil-oil
oil-oil GitHub avatar

beautify-github-readme

A GitHub Skill that redesigns repository READMEs by understanding the project, restructuring content, and generating project-native visual assets without inventing capabilities.

Python
711
NousResearch
Featured
NousResearch GitHub avatar

hermes-agent

Hermes Agent is an open-source, self-improving AI agent with a built-in learning loop that creates skills from experience, runs across platforms, and supports any LLM provider.

AI & Machine Learning
215,644