JuneYaooo /rea-video
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。
★ 9,420⑂ 1,388👁 19⑃ 21● 23▤ 1
+637
日增长
+4,423
周增长
9,420
stars
1,388
forks
19
watchers
21
prs
23
issues
1
releases
README
Reverse-engineer any video. Shot by shot: was it filmed, AI-generated or coded, and how to remake it. Every breakdown is written in VIDEO.md, an open format that agents read layer by layer. Website | 中文 | English | Русский | 日本語 | 한국어 | Español | Português | Français | Deutsch | Tiếng Việt | বাংলা !Python !Agent ⭐ Help more people find rea-video. Star this repo! Left: a TikTok ad shot on a phone. Right: an AI remake with another product. rea-video's verdict: the left is all live footage, one set and two camera positions; the right is all AI, 8 shots across 3 generations. Quick start rea-video is built for AI agents. In Claude Code, Codex or any agent that can run commands, say: text Install https://github.com/JuneYaooo/rea-video, then break down this video: /path/to/video.mp4 The agent installs the CLI, learns the workflow and runs the whole thing. You need ffmpeg and Python 3.10+. Breakdowns are fully upgraded. Each one gives you two outputs: - Report (report.html / PDF), for you: more reader-friendly, with a clearer structure, easier to learn from and to understand how the video was made and how to remake it. - VIDEO.md, for your AI: layered, so the AI reads only what a question needs and uses fewer tokens. You can also hook up a video-capable model (Gemini or Doubao both work) by giving the agent its endpoint and key. That makes the live/AI/3D calls more accurate and adds a reverse-engineered prompt for every shot. It works fine without one; if your agent can see images, it checks the uncertain shots itself. Reports are written in whichever language you ask in (Chinese or English). The example reports below are in English. What it can break down | Video type | Examples | What you get | |---|---|---| | Live footage | Talking-head, tabletop, handheld product demo, vlog, store visit | Setups and camera positions, framing, camera moves, lighting (12 setups with gear lists), color grade | | AI video | Text/image-to-video, AI short drama, AI music video | Evidence, a reverse-engineered prompt per shot, how to batch into generations and which model to use | | Avatar | A portrait driven by audio, lip-sync | Which shots are avatar shots, what portrait and audio you need | | 3D / animation | Blender / C4D explainers, product animation, 2D animation, stop-motion | Whether to generate with a video model or render from 3D code | | Code / template | Kinetic type, UI demos, charts, slide-style cards | Text, layout and motion timing, ready to rebuild as a Remotion project | | Screen recording | Software tutorials, web demos | Which parts are real material you'll need to record yourself | | Mixed / edits | AI characters + code UI + real screen capture; live footage with AI edits | Each shot judged separately, then reassembled on the original timeline | Besides how the visuals were made, every breakdown also covers: - Captions and styled text: start and end of each line (exports to SRT / ASS), plus color, outline and how the t
Top issues
#17求拆解-牌子3 comments · 2026-11-09#43[求拆解]1 comments · 2026-11-14#14minimax h3怎么复刻1 comments · 2026-11-08#8[求拆解]1 comments · 2026-11-05
Discussions
Latest release
v0.1.0 v0.1.0 2026-11-11视频拆解标准包 Reel,报告重写,音效单独分离 这一版定下了视频拆解的标准包格式:拆片包(Reel)。拆一条视频现在得到两样东西:给人看的报告(HTML / PDF),和给模型、下游项目读的拆片包。格式介绍和规范见 docs/reel.md。 拆片包 Reel - 四层逐级展开:卡片 → 概览和地图 → 时间线(一行一镜)→ 单镜文件,最后才是完整数据。一条 3 分钟口播读到概览约 2k token,完整数据约 19 万 token。 - 每个文件开头写着自己的 token 数;看到的和推断的分开写,时间线里推断的键名带 ~。 - 字段有 JSON Schema(rea_video/reel.schema.json)。rea-video reel out/ref --check 检查一个目录是否合格,reel.read() 读出结构化数据。 - 拆解时自动生成;旧的输出目录用 rea-video reel out/ref 补出来。 给人看的报告 - 从上往下:一句话结论 → 核心看点(开头怎么抓人、能火的几处做法,写明第几秒)→ 画面 / 包装 / 声音三层 → 叙事线 → 分镜表 → 照着复刻的步骤和每步细节 → 参考细节。每样信息只出现一次。 - 分镜表每镜分「画面里看得到的」和「工具推断的制作方式」。 - 判断依据写明是谁看的:工具测量、看图模型、AI 助手看图复核、