DEV.co
AI Frameworks · yvann-ba

ComfyUI_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.

Source: GitHub — github.com/yvann-ba/ComfyUI_Yvann-Nodes
701
GitHub stars
30
Forks
Python
Primary language
GPL-3.0
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositoryyvann-ba/ComfyUI_Yvann-Nodes
Owneryvann-ba
Primary languagePython
LicenseGPL-3.0 — OSI-approved
Stars701
Forks30
Open issues3
Latest releasev2.0 (2024-11-15)
Last updated2026-02-21
Sourcehttps://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.

Quickstart

Get the ComfyUI_Yvann-Nodes source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/yvann-ba/ComfyUI_Yvann-Nodes.gitcd ComfyUI_Yvann-Nodes# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Music Video Production

Generate AI-driven animations synchronized to music tracks, with visual elements responding to drums, vocals, or bass in real-time.

VJ/Live Performance Visuals

Create reactive background animations for live music events by mapping audio features to style transitions and content generation.

Generative Media Experimentation

Explore audio-visual synthesis by combining existing ComfyUI workflows (ControlNet, AnimateDiff) with audio-driven parameter automation.

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.

SignalAssessment
MaintenanceActive
DocumentationAdequate
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceHigh
Security considerations

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.

Software development agency

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.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

ComfyUI_Yvann-Nodes FAQ

Can I use this commercially?
Legally yes under GPL-3.0, but you must disclose source code and release modifications under GPL-3.0. Recommend legal review before SaaS/product deployment.
What audio formats are supported?
Not explicitly documented. Assume common formats (MP3, WAV) based on audio library conventions, but verify before production use.
Do I need a GPU?
Yes. Audio separation models and video generation require GPU acceleration. CPU-only deployment will be prohibitively slow. VRAM requirements unknown.
Is this a standalone tool or ComfyUI-only?
ComfyUI-only. It is a node pack extension; cannot run without ComfyUI. No REST API, CLI, or library export.

Custom software development services

Need help beyond evaluating ComfyUI_Yvann-Nodes? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and ai frameworks integrations — and maintain 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.