chiphoton/DeepSeek-Harness-Video-Director

Name: chiphoton/DeepSeek-Harness-Video-Director
Author: chiphoton

Plugin插件 Native原生 ⭐ 75 MIT Vision & Media视觉与多媒体 Prompts & Skills提示词与技能

🎬AI-Powered Director: MiniMax-H3 Video Generation Plugin Directed by DeepSeek-Harness. 🤖More than Prompting. 🪄Canvas UI.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

DeepSeek-Harness Video-Director is a DSH-native plugin built specifically for DeepSeek Harness, shipped with the bundle-manifest packaging and intended to be mounted into the web profile. Installation requires Git, Node.js ^22.19.0 or >=24, pnpm 11.7.0, and a working dsh CLI: clone the repository, run pnpm install --frozen-lockfile followed by pnpm run build, then register the plugin with dsh plugin --profile web add "file:$PWD" and launch it through dsh web, after which only dsh web is needed to bring the canvas up again. The plugin turns text, images, audio, video, previews, and saved outputs into connectable canvas elements called vd-nodes, with the overall graph referred to as a vd-workflow and ComfyUI-backed vd-nodes delegating to underlying comfyui-workflows.

Its core capability is a project-aware visual production graph that keeps each Video Project's canvas, chat session, jobs, immutable assets, and provider choices isolated. Beginners can drop into bundled image, H3 video, H3 audio, and prompt-enhancement workflows instead of hand-wiring every provider call, and the same project can mix Ollama, ComfyUI, OpenAI-compatible endpoints, Codex Plan, or one logical ComfyUI backend. Typical users are DSH operators who want a fully local, deployment-controlled multimedia pipeline (Qwen3.8-27B and MiniMax-H3 paths are highlighted as local-first options) as well as teams that need to direct script-to-video pipelines on an infinite canvas with explicit-save edits and per-project asset governance.

Dependencies are deliberately external: Ollama, ComfyUI, model weights, and remote API accounts must be supplied by the operator, with NVIDIA DGX Spark recommended for a fully local deployment but not strictly required. Limitations include a default 200 MiB upload cap per asset, retention of only the latest 100 job records per project, frozen snapshots for in-flight runs, UTC-stamped metadata, and reliance on the browser's download directory for the Save Output action. The plugin itself is MIT licensed, but MiniMax-H3 weights, ComfyUI, ComfyUI custom-node packages, and external services keep their own licenses, so operators must review each before commercial use and authenticate any remote Ollama, ComfyUI, or OpenAI-compatible endpoint before exposing it.

DeepSeek-Harness Video-Director 是一个专为 DeepSeek Harness 打造的 DSH 原生视频制作插件，使用 pnpm 构建后通过 dsh plugin --profile web add "file:$PWD" 持久挂载到 web profile，再用 dsh web 启动即可在 DSH Web 中加载。它把脚本、提示词、图像、音频、视频与 ComfyUI 工作流整合到同一张无限画布上，提供内置的图像、H3 视频、H3 音频与提示词增强模板，并支持本地 Ollama、ComfyUI、OpenAI 兼容接口与 Codex Plan 多个生成器混合编排。

典型流程是：先用 git clone --branch main --single-branch 拉取仓库并 pnpm install --frozen-lockfile && pnpm run build，然后在 Video-Director 的 Settings → Connections 中配置 Ollama（默认 127.0.0.1:11434，可选 Qwen3.8-27B）、ComfyUI（默认 127.0.0.1:8188）或 OpenAI 兼容端点，再用 vd-node 连出 vd-workflow，每个 Video Project 独立保存画布、会话、任务与不可变素材。它主要面向希望以可视化方式做本地化多模态视频导演的 DSH 用户，也适合需要在项目内隔离不同生成器与素材的研究与创作团队。

依赖方面，仓库仅提供编排逻辑与 UI，需要自备 Ollama、ComfyUI、模型权重、远程 API 账户以及 DSH CLI；NVIDIA DGX Spark 是推荐的全本地硬件，但非强制。上传素材默认上限为 200 MiB，每个项目保留最近 100 条任务，画布需显式保存，运行中的任务是冻结快照。MiniMax-H3 模型权重以及 ComfyUI 自定义节点各自保留独立许可证，导入 ComfyUI 工作流前应审查来源；插件本体采用 MIT 协议分发。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：DeepSeek-Harness-Video-Director（chiphoton/DeepSeek-Harness-Video-Director）
仓库：https://github.com/chiphoton/DeepSeek-Harness-Video-Director
本站详情页：https://www.yhbd.top/plugins/chiphoton-deepseek-harness-video-director/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 75 · 最近提交 2026-09-28 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号

This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号（星标、许可证、更新活跃度、清单完整度）

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:chiphoton/DeepSeek-Harness-Video-Director

把 chiphoton/DeepSeek-Harness-Video-Director 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

23.7 KB · 缓存于 2026-09-29 05:49:49 · 23.7 KB

简体中文 · Agent installation guide · Developer guide · Terminology · vd-node definitions · Example Gallery

DeepSeek-Harness Video-Director

🎬 DeepSeek-Harness Video-Director

A visual, node-based video director for DeepSeek Harness.
Script · Prompt · Image · Audio · Video · Fully local workflows

DSH Plugin · ComfyUI · Ollama · MiniMax-H3

DeepSeek-Harness Video-Director is a video-production plugin built for DeepSeek Harness. It turns script, image, audio, and video generation into a connectable canvas, with ready-to-use paths for ComfyUI, Ollama, OpenAI-compatible APIs, and Codex Plan.

Beginners can start with the built-in workflows instead of assembling every provider call by hand. Native Qwen3.8-27B and MiniMax-H3 paths make a fully local, deployment-controlled multimedia pipeline possible when the selected models and runtime support it.

We call canvas elements vd-nodes and the overall canvas graph a vd-workflow. A ComfyUI-backed vd-node executes a comfyui-workflow containing comfyui-nodes. See the terminology guide for definitions, packages, bindings, and execution IDs.

✨ Why Video-Director

Highlight	What you get
🧩 Visual production graph	Connect text, images, audio, video, workflows, previews, and saved outputs on one infinite canvas.
🚀 Beginner-ready workflows	Start from bundled image, H3 video, H3 audio, and prompt-enhancement workflows.
🏠 Local-first generation	Use Ollama and ComfyUI on your own machine, including Qwen3.8-27B and MiniMax-H3 pipelines.
🔌 Multiple providers	Mix Ollama, OpenAI-compatible endpoints, Codex Plan, and one logical ComfyUI backend in the same project.
🎞️ Project-aware direction	Every Video Project keeps its own canvas, chat session, jobs, immutable assets, and provider choices.
🌐 Language and storage	Switch between English and Chinese, and relocate canvas data from Settings.
🛠️ Extensible by design	Import reviewed API-format comfyui-workflows or package them as declarative vd-node packs.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 chiphoton/DeepSeek-Harness-Video-Director 的 README.md。在 GitHub 查看原文 →