# pyang5166/gbro-collage-broll

> 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

- GitHub: https://github.com/pyang5166/gbro-collage-broll
- Category: Generative Media (https://ideas.asveas.com/c/genmedia); also AI Agents
- Tags: agent-skill, broll, gemini, paper-collage, video-generation, python
- Language: Python · License: MIT
- Stars: 1,895 · Forks: 167 · Open issues: 4
- Last push: 2026-07-15 (4 months ago)
- Vibe score: 55/100

## What it is
Turn a ~5s voiceover line into a premium editorial paper-collage assemble-from-empty B-roll clip, powered by Gemini Omni Flash first/last-frame video generation. 视频生成脚本（scripts/generatevideo.py + scripts/uploadfile.py）已随 skill 自带，无需额外安装其他 skill。

## When to use it
Reach for gbro-collage-broll when your project generates or processes images, video, speech or audio — it's written in Python and fits stacks tagged agent-skill, broll, gemini, paper-collage.

## Maintenance
pyang5166/gbro-collage-broll looks actively maintained: the last push was 4 months ago (2026-07-15), with 1,895 stars and 4 open issues.

## Quick start
```bash
git clone https://github.com/pyang5166/gbro-collage-broll.git
```

## Alternatives in Generative Media
- [yt-dlp/yt-dlp](https://github.com/yt-dlp/yt-dlp) — A feature-rich command-line audio/video downloader (★207k, Python, vibe 99/100) · details: https://ideas.asveas.com/r/yt-dlp/yt-dlp
- [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI) — The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. (★146k, Python, vibe 98/100) · details: https://ideas.asveas.com/r/Comfy-Org/ComfyUI
- [remotion-dev/remotion](https://github.com/remotion-dev/remotion) — 🎥      Make videos programmatically with React (★72.5k, TypeScript, vibe 94/100) · details: https://ideas.asveas.com/r/remotion-dev/remotion
- [ggml-org/whisper.cpp](https://github.com/ggml-org/whisper.cpp) — Port of OpenAI's Whisper model in C/C++ (★55.1k, C++, vibe 89/100) · details: https://ideas.asveas.com/r/ggml-org/whisper.cpp
- [lemomo-ai/lemo-opuscar](https://github.com/lemomo-ai/lemo-opuscar) — A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱：66 种现成风格，也能做出你自己的 (★14.8k, JavaScript, vibe 87/100) · details: https://ideas.asveas.com/r/lemomo-ai/lemo-opuscar
- [deepbeepmeep/WanGP](https://github.com/deepbeepmeep/WanGP) — A fast AI Video Generator for the GPU Poor. Supports Minimax H3, LTX-2.3/2.5, Wan 2.1/2.2,  Qwen Image 1/2, Krea 2, Hunyuan Video, LTX  Video and Flux. (★11.6k, Python, vibe 82/100) · details: https://ideas.asveas.com/r/deepbeepmeep/WanGP

---
Source: https://ideas.asveas.com/r/pyang5166/gbro-collage-broll · Catalog: https://ideas.asveas.com/llms.txt