AI 工具AI TOOLS· IMAGE-VIDEO
openjutsu
D3voz/openjutsu
一键替换视频中的人物角色，开源本地运行，用ComfyUI和MiniMax H3实现。An open-source tool that swaps any character in a video with one click, running locally on your GPU.
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
- 适用平台Platforms
- 未确认Not confirmed
- 已识别的要求Documented requirements
- API key · Local runtime
- 许可LICENSE
- MIT
能力CAPABILITIES
它能帮你做成什么What it helps you do
- 01
一键替换视频中的人物角色
- 02
重新调整视频人物的光线
- 03
在本地电脑上完成视频换脸
- 01
Swap any character in a video with one click
- 02
Run everything on your own GPU
- 03
Use open-weight video generation models
- 04
Relight swapped characters automatically
上手GET STARTED
怎么装How to install
pip install comfy-api-proxy==0.1.6选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
限制与风险Limits and risk
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
- 01需要 API KeyREQUIRES API KEY
- 是Yes
- 02需要本地环境NEEDS LOCAL RUNTIME
- 是Yes
- 03需要 DockerNEEDS DOCKER
- 未在文档中发现Not found in the docs
- 04难度DIFFICULTY
- 需要本地环境Needs a local runtime
- 05许可LICENSE
- MITMIT
- 06阶段STAGE
- 新发布New
- 创建于 26 OCT 2026Created 26 OCT 2026
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险，但不代表安全The static scan of the documentation found no known risk patterns, but that does not prove the code is completely safe.
项目动态PROJECT ACTIVITY
它现在处在什么位置Where it stands right now
首次发现FIRST SEEN
30 OCT 202630 OCT 2026
增长GROWTH
+109.8%+109.8%
584 → 1.2k stars · 4 个快照584 → 1.2k stars · 4 snapshots
状态STATUS
新发布New
质量 A-Quality A-
项目在GitHub上已获得1040颗星和154次fork，社区关注度高。Open-source alternative to Higgsfield Genjutsu
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
- 来源 URLSource URL
- https://github.com/D3voz/openjutsu
- 原始数据哈希Raw data hash
- d653dcf93304af134eb85540f3826a21
- 解析时间Parsed at
- 2026-10-30T23:42:31.702Z
- 最后一次验证Last verified
- 2026-11-02T22:14:53.144Z
- 增长测量时间Growth measured
- 2026-11-02T00:05:43.580Z
- 发现查询Discovery queries
- focus:play:repo:video-generation
- 分类来源Category source
- rules
- 焦点Focus
- play · web (5)
依赖：Dependencies:@comfyorg/sdk, next, react, react-dom
完整解析证据 JSONFull parse evidence JSON
{
"agents": [],
"apiKey": "ttp://127.0.0.1:8189`. Leave `COMFY_API_KEY` empty for a local proxy. The base mode",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 4,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "ai-tools",
"secondary": "image-video"
},
"localRuntime": "s on open weights on your own GPU: MiniMax H3 for the video, SAM 3.1 to t",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 4,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}