ZeroHackz/OpenFlowFrames

Name: ZeroHackz/OpenFlowFrames
Author: ZeroHackz

Plugin插件 Native原生 ⭐ 3 GPL-3.0 Vision & Media视觉与多媒体

This project is a fork of the original Flowframes by n00mkrad. Huge thanks to him for creating and maintaining the powerful core of this application!

catalog descriptioncatalog 简介 / catalog description：Video Frame Interpolation for Windows

Project Overview项目介绍

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

OpenFlowFrames is a native DeepSeek Harness plugin that also provides a standalone video frame interpolation tool for Windows. It is a lean, free open-source fork of the original n00mkrad Flowframes project, built around the latest RIFE interpolation models that are fully bundled within the repository, so no external model downloads or servers are required. It works with any GPU from AMD, Intel, or NVIDIA via rife-cnn-vulkan, and does not require CUDA or PyTorch to be installed on your host system to run properly.

Casual users can run the tool as a standalone desktop app with a clean dark-mode CustomTkinter GUI. To launch the GUI, you just clone the repository locally and double-click the launcher-gui.bat file, which will automatically set up a local virtual environment on first run before opening the main interface. You can input a single video file or a folder of still frames, choose your preferred interpolation factor and RIFE model, then export the final result as an H.264 MP4 with original audio preserved or a sequence of PNG frames.

To install OpenFlowFrames as a DSH plugin, run the command dsh plugin add github:ZeroHackz/OpenFlowFrames in your terminal. The only core system requirement for the plugin is Python 3.10 or newer, or you can set the OPENFLOWFRAMES_PYTHON environment variable to point to your existing compatible Python installation. All required RIFE models are bundled directly in the repository, so no extra downloads are needed after installation, and the project is released under the open-source GPL-3.0 license with no monetization or paywalled features.

这是一个面向 DeepSeek Harness (DSH) 的原生插件，同时提供可独立运行的 Windows 平台视频插帧工具，基于原 Flowframes 项目重构开发，集成了最新的 RIFE 插帧模型，无需调用外部模型服务，支持 AMD、Intel、NVIDIA 全品牌 GPU，不依赖 CUDA 或 PyTorch 环境。

普通用户可以直接通过图形界面导入视频或帧序列，选择插帧模型和倍率后即可输出带音频的 MP4 视频或 PNG 序列帧，AI 生成内容创作者可以用它处理生成的单帧图片，工具会自动归一化不同分辨率、不同位深的输入图片，方便最终生成流畅的高帧率视频。

项目采用 GPL-3.0 开源协议，完全免费无任何付费门槛，作为 DSH 插件可通过 dsh plugin add github:ZeroHackz/OpenFlowFrames 命令一键安装，运行依赖 Python 3.10 及以上版本，所有模型已打包在仓库中，无需额外下载，也支持独立打包便携版可执行文件。

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：OpenFlowFrames（ZeroHackz/OpenFlowFrames）
仓库：https://github.com/ZeroHackz/OpenFlowFrames
本站详情页：https://www.yhbd.top/plugins/zerohackz-openflowframes/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 GPL-3.0 · ⭐ 3 · 最近提交 2026-08-13 · 主语言 Python

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 1 warning1 项注意

Only 3 stars - very few users, little community feedback星标只有 3，几乎没人在用，遇到问题缺少社区反馈

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 add github:ZeroHackz/OpenFlowFrames

把 ZeroHackz/OpenFlowFrames 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

4.2 KB · 缓存于 2026-08-23 03:42:04 · 4.2 KB

OpenFlowFrames - Video Frame Interpolation for Windows

This project is a fork of the original Flowframes by n00mkrad. Huge thanks to him for creating and maintaining the powerful core of this application!

This fork is a lean, fully free and open reimagining: a modern Python GUI around the latest RIFE models — no Patreon tiers, no paid builds, no legacy codebase.

Screenshot

Main interface: pick a video or a folder of frames, choose a model and factor, interpolate.

Main interface

✨ Features

Latest RIFE Models: RIFE 4.9 through 4.26 bundled in the repo — no external model server, fully self-contained.
Any GPU: Runs on AMD, Intel, and NVIDIA via rife-ncnn-vulkan — no CUDA or PyTorch required.
Modern GUI: A clean CustomTkinter dark-mode interface — no install needed beyond Python.
Video or Frame-Folder Input: Interpolate a video file, or a directory of PNG/JPG/WebP frames with a custom input framerate.
MP4 or PNG Output: Encode to H.264 MP4 (audio preserved) or export the interpolated frames as a PNG sequence.
Robust Frame Handling: Mixed resolutions and alpha/16-bit PNGs (common in AI-generated frames) are normalized automatically.
Portable Windows Executable: Build a self-contained portable app with one script — no Python needed on the target machine.
No Monetization: Fully free; no Patreon/PayPal integrations.

💻 How to Use (Easy Way)

Python GUI (recommended):

Clone this repository:

git clone https://github.com/ZeroHackz/OpenFlowFrames.git

Double-click launcher-gui.bat — it sets up a virtual environment on first run and launches the GUI.

Portable build:

Run build-portable.bat. The result in dist/ is fully self-contained:

dist/
  OpenFlowFramesPortable.exe
  packages/av/           (ffmpeg)
  packages/rife-ncnn/    (interpolator + bundled RIFE models)

Copy the dist folder anywhere and double-click the exe.

How It Works

ffprobe reads the input framerate and frame count (or you provide the FPS for a frame folder).
ffmpeg extracts frames (skipped for frame-folder input).
rife-ncnn-vulkan interpolates to frames × factor.
ffmpeg encodes H.264 at the multiplied framerate, copying the original audio — or the frames are exported as PNGs.

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 ZeroHackz/OpenFlowFrames 的 README.md。在 GitHub 查看原文 →