velorn
starsforks
How to install velorn?
velornlabs/velorn
$git clone https://github.com/VelornLabs/velornThe open-source AI video workstation — a real editor for you, and 100+ MCP tools for your agent.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | # Velorn |
| 4 | |
| 5 | **The open-source AI video workstation — a real editor for you, and 100+ MCP tools for your agent.** |
| 6 | |
| 7 | [](https://github.com/VelornLabs/velorn/releases/latest) |
| 8 | [](LICENSE) |
| 9 | [](https://github.com/VelornLabs/velorn/releases/latest) |
| 10 | |
| 11 | [](https://velorn.ai) |
| 12 | [](https://x.com/getvelorn) |
| 13 | [](https://discord.gg/QWZUuUChVK) |
| 14 | |
| 15 | [](https://github.com/VelornLabs/velorn/releases/latest) |
| 16 | [](https://github.com/VelornLabs/velorn/releases/latest) |
| 17 | [](https://github.com/VelornLabs/velorn/releases/latest) |
| 18 | |
| 19 | English · [Español](docs/i18n/README.es.md) · [简体中文](docs/i18n/README.zh-CN.md) · [日本語](docs/i18n/README.ja.md) · [한국어](docs/i18n/README.ko.md) · [Português (Brasil)](docs/i18n/README.pt-BR.md) · [Français](docs/i18n/README.fr.md) |
| 20 | |
| 21 | </div> |
| 22 | |
| 23 | <p align="center"><img src="docs/readme/agent-editing.gif" alt="One prompt: Claude builds the edit in Velorn via MCP" width="860"></p> |
| 24 | <p align="center"><i>One prompt. The agent generates media, builds the timeline, and mixes the audio — live, via MCP.</i></p> |
| 25 | |
| 26 | Velorn is an open-source desktop AI video workstation for creators who use ComfyUI. It brings planning, generation, asset management, timeline editing, captions, effects, and export into one project-based app. |
| 27 | |
| 28 | Use built-in local and cloud workflows, bring your own ComfyUI API workflow JSON, or install the bundled Velorn Bridge so a graph open in ComfyUI can be sent back into Velorn. |
| 29 | |
| 30 | <p align="center"> |
| 31 | <img src="docs/readme/editor-timeline.png" alt="Velorn editor with generated assets, preview, timeline tracks, and inspector" /> |
| 32 | </p> |
| 33 | |
| 34 | ## What Velorn Is For |
| 35 | |
| 36 | - Creating music videos from lyrics, timing, characters, keyframes, video shots, and timeline edits. |
| 37 | - Building UGC-style creator ads and small-business ads with editable shot plans. |
| 38 | - Running curated local and cloud image/video workflows from one Generate workspace. |
| 39 | - Running custom ComfyUI image, video, keyframe, and music-video workflows inside the app. |
| 40 | - Editing generated clips with tracks, transitions, effects, captions, proxy/cache tools, and export. |
| 41 | - Keeping generated media, prompts, workflow outputs, and timelines organized inside a project. |
| 42 | |
| 43 | Velorn is not a replacement for ComfyUI. It is the production layer around ComfyUI: plan the work, send jobs to ComfyUI, collect the outputs, and finish the edit. |
| 44 | |
| 45 | <p align="center"> |
| 46 | <img src="docs/readme/create-workflows.png" alt="Velorn Create workspace with UGC, business ad, music video, and short film creators" /> |
| 47 | </p> |
| 48 | |
| 49 | ## Download |
| 50 | |
| 51 | Most users should download the packaged desktop app from the [GitHub Releases page](https://github.com/VelornLabs/velorn/releases). |
| 52 | |
| 53 | Release assets include: |
| 54 | |
| 55 | - `Windows Installer` |
| 56 | - `Windows Portable` |
| 57 | - `Mac (Apple Silicon)` |
| 58 | - `Mac (Intel)` |
| 59 | - `Linux AppImage` |
| 60 | - `Linux deb` |
| 61 | |
| 62 | Ignore GitHub's auto-generated source-code archives unless you plan to build Velorn from source. |
| 63 | |
| 64 | ## Main Features |
| 65 | |
| 66 | ### Generate |
| 67 | |
| 68 | Generate runs built-in local workflows, cloud/partner workflows, and custom ComfyUI workflows. |
| 69 | |
| 70 | - Local image, video, image-edit, audio, and utility workflows. |
| 71 | - Cloud workflows such as Nano Banana 2, GPT Image 2, Seedance, |
People who liked this also viewed
6 picksType
- elevenlabs-mcpThe official ElevenLabs MCP serverMCP ServersJul 2026
- MonetEdit Videos and Design Images with Claude code or CodexMCP ServersJul 2026
- scribe.jsJavaScript OCR and text extraction for images and PDFs.MCP ServersJul 2026
- gliana-aiPay-per-call generative AI — 60+ models (image, video, music, speech). No signup, no API key; pay per call from your wallet over MPP/x402.MCP Serversrecently
- nanobanana-mcp-serverAI image generation MCP server powered by Google Gemini, with smart model selection and 4K outputMCP ServersMay 2026
- FramesailCreate long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot. Making long-form MCP Serversrecently
