# D3voz/openjutsu

> A local web app for swapping characters and objects in videos: drop a video and a character photo, and the main person in the frame is replaced by your character while camera, cuts and soundtrack stay intact. Runs on your own GPU via ComfyUI and open-weight models MiniMax H3, SAM 3.1 and Qwen3-VL.

- Magnitude: 4.4 out of 10 — Early signal
- Stars: 138 total · +16 stars measured 2026-10-28, 20:25–21:54 UTC
- Star trust: star growth looks organic
- Category: Generative media · Language: TypeScript · License: MIT · Created: 2026-10-26 · Last push: 2026-10-28
- GitHub: https://github.com/D3voz/openjutsu · Page: https://gitnova.dev/en/r/D3voz/openjutsu

## Useful for

- Replace the main person in a clip with your own character from a single photo
- Change a person's clothes, hair or background in a video without reshooting
- Remove an object from a shot or swap it for another using SAM masks

## Why it’s here

- Star-counter measurements on 2026-10-28 (UTC), 20:25–21:54: 122 → 138 stars (+16). This is the change over that interval.
- Estimated end-of-day forecast: about +18 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 138 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #159.
- About 17 forks a day — people are taking the code.
- Recent forks include notable developers: @rudycelekli (627 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 22
- Issues and pull requests: 21
- Watchers: 2
- Average over the last week: 28 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 12

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-26 … 2026-10-28: 0, 66, 16

## Spotted in now

- Top new repositories this week: #159

## More in this category

1. **anhao/ai-pose-gallery-zh** — 8.2 · Breakout · Generative media · HTML · +1,460 stars measured 2026-10-28, 00:02–21:53 UTC
   Chinese localization of an AI pose reference gallery: 1439 records and 2878 images with a ready-to-deploy dependency-free static site. Useful for artists and 3D modelers picking poses.
   Full card: https://gitnova.dev/en/r/anhao/ai-pose-gallery-zh.md
2. **toyxyz/toyxyz_RGBMocap** — 5.7 · Early signal · Generative media · Python · +120 stars measured 2026-10-28, 00:02–21:53 UTC
   Native Windows app for video motion capture: reconstructs 3D human animation with ExMR, FlowHMR and GVHMR models, corrects contacts and exports FBX/VMD.
   Full card: https://gitnova.dev/en/r/toyxyz/toyxyz_RGBMocap.md
3. **debpalash/VoiceStudio** — 5.2 · Steady · Generative media · Python · +1,571 stars measured 2026-10-28, 00:02–21:53 UTC
   A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11 ASR engines, a…
   Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md
4. **0xS4N4TG/kinetograph** — 5.0 · Early signal · Generative media · TypeScript · +116 stars measured 2026-10-28, 00:03–21:53 UTC
   A programmatic video engine in TypeScript with a Rust GPU compositor: renders video from code, supporting Remotion API, CSS, SVG, Canvas 2D, WebGL, and Web Audio.
   Full card: https://gitnova.dev/en/r/0xS4N4TG/kinetograph.md
5. **heygen-com/hyperframes** — 4.7 · Steady · Generative media · TypeScript · +741 stars measured 2026-10-28, 00:02–21:53 UTC
   Framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos. Runs locally via CLI or from AI coding agents through a set of skills.
   Full card: https://gitnova.dev/en/r/heygen-com/hyperframes.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-28 22:04 UTC, updated every 30 minutes.