VideoFree Studio Connect people, agents, and ComfyUI into one creative pipeline.
VideoFree Studio is an AI creation hub that runs on your own computer: people create in the workspace, agents call in over MCP, and ComfyUI executes underneath — all three sharing one set of capabilities. Generation, the editor, even canvas nodes are plugins: register once and both humans and AI can use them, straight from plain language to final cut.
Install VideoFree Studio on this computer: download the latest release from https://github.com/linpengishero/VideoFreeStudio/releases and extract it to [folder] (or clone the repo), follow README.md for my OS, then start it — double-click videofree.bat on Windows, or ./videofree.sh on Linux. Open http://127.0.0.1:8765 to confirm the workspace is up, then tell me what is still missing: the ComfyUI address, the plugins to install, and the models each plugin INSTALL.md declares (fetch them from Hugging Face or the official source). If a download needs a login, terms acceptance, or payment, stop and let me handle it.
Local AI is powerful — and still hard to use
Cloud products pick the models and flow for you; going local turns you into a workflow maintainer. VideoFree Studio adds a stable product layer on top of ComfyUI — from install to final cut, with zero dependencies to start.
Workflows as plugins
Turn a ComfyUI workflow you have debugged into a plugin: models, node graphs, parameter UI, and assets live in one plugin folder — copy it into plugins/, restart the gateway, done. The moment it registers, it is an MCP tool: users pick the capability in the workspace, agents call it directly.
core — plugin.jsonPlain-language creation
Each plugin carries collaboration skills that ask, refine, and compile natural language into the execution prompt the model actually needs.
Local + cloud, one gateway
Local model plugins and cloud API plugins run under one gateway and one project — switch per shot, never locked to a single source.
Project-based management
Project → category → asset: scripts, prompts, jobs, and reusable assets all save with the project; final media auto-archives, and regenerating restores the exact prompt and parameters.
MCP: any AI can call it
MCP ships with the gateway — paste one URL and Claude Code, Codex, or Doubao can discover capabilities, launch generations, and manage projects. 30+ tools cover the whole workspace, and every registered plugin lands in the tool surface with zero MCP-side config.
Timeline editing & final cut
A built-in editor: five tracks — main, overlay, audio, captions, text — with transitions, waveform mixing, and one-click transcription; FFmpeg renders the final cut in-project.
Infinite Canvas: wire capabilities into pipelines
Image, video, speech, agents, and resource processing become canvas nodes — connect to compose, run with one click, resume after failures. Nodes are plugins; existing capabilities plug in unchanged.
in development Explore Infinite Canvas →The demo plugins are just the start — you define the capabilities
The repository ships demo plugins across image, video, speech, music, and post-production, showing what one plugin can package. Turning your own debugged ComfyUI workflow into a plugin is the real VideoFree Studio workflow.
- krea2
- qwen-image
- gpt-image
- minimax-h3
- ltx-2.5
- cosyvoice3
- qwen-tts
- ace-step
- minimax-music
- video-post
- film-studio
- image-split
- project-archive
- ai-project-progress
From install to full automation
Eight bilingual tutorials: install and use plugins, connect over MCP, then take the demo skill apart and build your own fully automated video pipeline.
Installation
One prompt to your agent: download, launch, SageAttention, missing-model audit — done. Step-by-step reference included.
Read → 02 /Install Plugins
Copy a folder, restart the gateway; an AI agent downloads models per INSTALL.md.
Read → 03 /Build Plugins
Development is an agent job too: the repo ships the skill — analyze, implement, test; registered plugins land in MCP automatically.
Read → 04 /MCP Setup
Let any MCP-capable AI call generation, queries, and project management directly.
Read → 05 /Narrow MCP
Wrap the HTTP API down to the few tools your pipeline needs — steadier full automation.
Read → 06 /Demo Skills
story-video-skill + OpenMontage — hand the whole video pipeline to an agent.
Read → 07 /Long-Video Skill Dev
Take the demo skill apart — final-package-first, stage gates, guarded submission — and build your own.
Read → 08 /FAQ
Missing nodes or models, VRAM limits, LAN connections, and other fixes.
Read →Start your first project now
The Windows release runs straight from the extracted folder — no Python or Node.js needed. Join the community and get help anytime.
Open source under AGPL-3.0
GitHub · releases and source