JuneYaooo/rea-video

rea-video

Reverse-engineer any video.

Talking-head, tabletop, AI video, 3D, motion graphics, mixed edits: give it any of them,
and it tells you shot by shot how the visuals, styled text, editing and audio were made, then gives you a plan to make one yourself.

中文 | English | Русский | 日本語 | 한국어 | Español | Português | Français | Deutsch

Left: a TikTok ad shot on a phone. Right: someone's AI remake with a different product swapped in.
rea-video's verdict: the left is all live footage, one set and two camera positions; the right is all AI-generated, and its 8 shots can be produced in 3 generations.

Reports come out in the language you ask in (Chinese or English; your agent passes --lang). The detailed docs are in Chinese for now; your agent reads them and answers in your language. The six example reports below are in English, so you can see what a report looks like without installing anything.

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 picture was made, every video also gets:

• Captions and styled text: start and end of each line (exports to SRT / ASS), plus color, outline and how the text comes in
• Stickers, emoji, picture-in-picture: where they sit and how long they stay
• Editing: where the cuts are, how fast, whether they hit the beat
• Audio: human or AI voice, AI or library music and its BPM, where each sound effect lands
• Material you'll supply yourself: screen recordings, screenshots, product photos

Quick start

rea-video is built for AI agents. In Claude Code, Codex or any agent that can run commands, say:

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+.

brew install ffmpeg            # or: sudo apt install ffmpeg
git clone https://github.com/JuneYaooo/rea-video && cd rea-video
bash scripts/install_skill.sh  # installs the CLI (pip, or pipx / a local .venv if pip is blocked) and links the skill into ~/.claude, ~/.codex, ~/.agents
rea-video --help

You get:

• a one-line summary, e.g. "41% AI video + 59% code UI, 8 s of real screen recording, library music at 122 BPM"
• a remake plan, split into what to film, what to generate and what to code
• a full report.html with per-shot frames, evidence, prompts, camera and lighting notes, and the audio breakdown

Examples

Mixed-media clip · 19 s · 10 shots AI characters talking + code-built UI + 8 s of real screen recording. The 5 dialogue shots are split up by UI segments but share one set, so one generation covers them. Video · Report	3D explainer · 67 s · 21 shots All 3D, AI narration. Doable as 10 video generations, or have an LLM write Blender / Three.js code. Video · Report
Product promo · 70 s · 12 shots 83% code-driven motion graphics, 12% screen recording. No video model needed; one Remotion project does it. Video · Report	AI music video · 165 s · 86 shots Correctly flags the song as AI-generated (it was made with Suno). The vision model called some shots "live-action drama"; the agent spotted fake Chinese characters on a scroll and ruled them AI. Video · Report
Live-action unboxing · 72 s · 29 shots All real footage: an overhead phone rig, one rug, one camera position, no voice-over, room sound plus library BGM. After platform transcoding the offline tool called 35% of it AI; agent review brought it to 97% live-action. Video · Report	AI + real person hybrid · 58 s · 21 shots 75% real (talking head + filming a phone screen) and 25% AI: the creator fed her own on-camera clip and two product photos to Jimeng to generate a "real-person" product segment. The AI part was caught by the Jimeng watermark and garbled text on the gift box. Video · Report

Remakes

After rea-video breaks a video down, the remake recipe in cheap-claude-video generates a new version: camera, motion, pacing and transitions follow the original, only the elements you choose are swapped. These results were generated with a self-hosted MiniMax H3: the original shot is the motion reference, and keyframes with the swapped elements (gpt-image-2) set the look. Below are three remakes that OiiOii showed in its WeChat articles. For each we made two versions: the same swap as OiiOii, and one that also swaps the subject, setting and props. Each GIF plays four versions in sync: original, OiiOii remake, our remake, element-swap version.

Overhead outfit change · 12 s Same swap: woman → man, three outfits → matching menswear. Element swap: a girl in three historical Hanfu outfits in a Chinese study; the remote becomes a round fan. HD comparison video (with audio) · same-moment stills

Paper-craft / watercolor animation · 30 s Same swap: new clay girl as the lead. Element swap: a fox; forest → coral reef, clouds → starry sky, sunset → aurora. HD comparison video (with audio) · same-moment stills

Handheld product video · 21 s · 11 shots Same swap: an original new product, English sticker → Chinese caption. Element swap: pink product, kitchen → camping table, new ingredients. HD comparison video (with audio) · same-moment stills

The HD comparison videos use the original audio. The originals and OiiOii versions come from the articles and are shown for comparison only.

Accuracy

How-it-was-made accuracy, weighted by shot duration:

| | Tuning set (15) | Holdout (16) | Re-encoded WeChat videos (10) | |---|---|---|---| | Tools only (offline, free) | 98.3% | 99.6% / 98.9% | 88.6% | | + vision model (Gemini) | — | 99.6% / 99.8% | 99.6% | | + agent visual review | — | 99.6% / 99.8% | 100% |

The two holdout numbers are holdout (9 videos) and holdout2 (7 videos).

On original files the tools alone are mostly enough. Videos downloaded from platforms have been recompressed, which wipes out the noise evidence, so it takes a vision check to get back above 99%.

Real-asset detection is 97–99%, and shot boundaries are all correct. Numbers and how to reproduce them: eval/RESULTS.md.

How it works

1. Split: cut the video into shots and separate audio into voice, music and effects. 2. Gather evidence: measure the frames (frame cadence, sensor noise, whether the whole image is panning as one plane, AIGC tags in metadata); look at the images (hands, text, physics); listen (BPM, key, singing vs speech). 3. Decide: hard evidence like AIGC tags and frame cadence outranks "looks like". Conflicts are flagged for the agent to review visually. 4. Plan the remake: batch shots according to what the target video model can actually do, such as max clip length, multi-shot support and how many reference images it takes.

FAQ

Docs

• docs/what-it-detects.md: everything it detects (10 visual types, camera, lighting, grade, audio)
• docs/replicate.md: remaking from the report
• docs/cases.md: case details
• docs/decompose.md: detection rules
• docs/cli.md: CLI usage and capsule-cinema integration
• rea_video/capabilities/: capability tables for video / image / audio models, used to pick models for the remake plan
• eval/RESULTS.md: eval results

Community

Questions, breakdowns and remake ideas: GitHub Discussions. Chat with us on Discord. Chinese speakers can also find us on linux.do.

Want a video broken down? Open a request issue with the link and we'll publish the result as a case.

Credits

Inspired by REA (Reverse Engineer Anything): trace from what you see back to how it was made, back every claim with evidence, and verify by measurement.