AI ERP with agents inside the systems you run
AI phone and voice agents for real calls
LLM.coPrivate, self-hosted LLM deployments
Legal AI infrastructure for firms
AI RFP discovery and response drafting
Automatic.coBusiness process automation
CyberAttack.aiThreat detection and defense
Secure AI virtual data roomsComfyUI_Yvann-Nodes
ComfyUI_Yvann-Nodes is a Python package that adds audio-reactivity capabilities to ComfyUI, enabling users to generate AI-driven animations that synchronize with music. It provides nodes for audio analysis, peak detection, and dynamic transitions, working with existing ComfyUI models like IPAdapter, AnimateDiff, and ControlNet.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Repository | yvann-ba/ComfyUI_Yvann-Nodes |
| Owner | yvann-ba |
| Primary language | Python |
| License | GPL-3.0 — OSI-approved |
| Stars | 701 |
| Forks | 30 |
| Open issues | 3 |
| Latest release | v2.0 (2024-11-15) |
| Last updated | 2026-02-21 |
| Source | https://github.com/yvann-ba/ComfyUI_Yvann-Nodes |
What ComfyUI_Yvann-Nodes is
A GPL-3.0 licensed ComfyUI extension written in Python that implements audio separation (HybridDemucs, OpenUnmix), audio-to-weight mapping, peak detection, and prompt scheduling to drive generative AI video workflows. Nodes handle audio analysis, image/video-to-video transitions, and dynamic parameter control based on audio features.
Get the ComfyUI_Yvann-Nodes source
Clone the repository and explore it locally.
git clone https://github.com/yvann-ba/ComfyUI_Yvann-Nodes.gitcd ComfyUI_Yvann-Nodes# follow the project's README for install & configurationNeed it deployed, integrated, or customized instead? DEV.co ships production installs.
Best use cases
Implementation considerations
- Requires ComfyUI installation (Mac, Windows, Linux) and download of audio separation models (HybridDemucs or OpenUnmix) before first use.
- GPU/VRAM requirements unknown; audio separation and video generation are resource-intensive—test on target hardware early.
- Workflow-first design: users must load provided JSON templates; custom node graphs require understanding of audio weight mapping and peak detection logic.
- Audio separation accuracy varies by model and source; threshold/multiply parameters need tuning per use case.
- GPL-3.0 copyleft clause: any derivative modifications or integrated workflows must remain open-source unless dual-licensed.
When to avoid it — and what to weigh
- Closed-source Commercial Deployment — GPL-3.0 requires source code disclosure and derivative works to be licensed under GPL-3.0. Commercial use requires compliance review or dual licensing negotiation.
- Proprietary Workflow Integration — If your project relies on proprietary AI models or closed-source ComfyUI extensions, licensing conflicts may arise.
- Low Latency / Real-Time Requirements — Audio separation and analysis models incur computational overhead; unsuitable for sub-100ms real-time audio-to-visual latency needs.
- Non-English Speaker Support — Documentation and node parameters are English-only; limited accessibility for non-English-speaking teams.
License & commercial use
GPL-3.0 (GNU General Public License v3.0). This is a copyleft license: modifications and derivative works must be licensed under GPL-3.0 and source code must be made available to users. Commercial use is legally permissible but triggers disclosure obligations.
Commercial use is allowed under GPL-3.0, but requires careful assessment: (1) if you modify or integrate the code, you must release modifications under GPL-3.0; (2) if you distribute it (even internally), you must provide source code and license terms; (3) if you deploy as a SaaS, AGPL considerations may apply under network use clauses. Recommend legal review before commercial adoption. No commercial support, SLA, or indemnification stated.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Adequate |
| License clarity | Clear |
| Deployment complexity | Moderate |
| DEV.co fit | Good |
| Assessment confidence | High |
Code execution risk: user-supplied audio and image inputs are processed by third-party audio separation models (HybridDemucs, OpenUnmix). No stated input validation, sanitization, or sandboxing. GPU resource exhaustion risk if batch_size or fps parameters are not bounded. Dependency chain (ComfyUI, audio libraries) not audited in provided data. No security policy or disclosure process documented. Self-hosted deployment mitigates cloud-side risks.
Alternatives to consider
Runway ML or Pika Labs (Commercial SaaS)
Proprietary video generation with audio sync, no deployment hassle, commercial support, but closed-source and higher cost.
Deforum Stable Diffusion Scripts + Audio-Reactive Plugins
Open-source audio-reactive animation toolkit; more mature ecosystem, but steeper learning curve and less ComfyUI integration.
Custom WebGL/Three.js + OpenAI Whisper + CLAP (DIY)
Build proprietary audio-visual engine with fine-grained control; highest implementation effort but maximum flexibility and IP ownership.
Build on ComfyUI_Yvann-Nodes with DEV.co software developers
Integrate ComfyUI_Yvann-Nodes into your generative media workflow. Contact our team to assess licensing, deployment, and architecture for your use case.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
ComfyUI_Yvann-Nodes FAQ
Can I use this commercially?
What audio formats are supported?
Do I need a GPU?
Is this a standalone tool or ComfyUI-only?
From evaluation to production software
Need help beyond evaluating ComfyUI_Yvann-Nodes? DEV.co is a software development agency building custom software, web applications, APIs, and ai frameworks integrations — and maintaining them long-term.
Ready to Build Audio-Reactive AI Visuals?
Integrate ComfyUI_Yvann-Nodes into your generative media workflow. Contact our team to assess licensing, deployment, and architecture for your use case.