This repository provides a Safetensors version of the MelBandRoFormer model optimized for integration with ComfyUI via a dedicated custom node. It is used primarily for audio source separation tasks such as isolating vocals or instruments. The model is popular among AI audio creators using node-based interfaces.
In the Image generation space, MelBandRoFormer Comfy takes a focused approach. It focuses on performing high-quality audio source separation within the ComfyUI visual workflow environment. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web and API.
It is developed by Kijai, and it first shipped in 2025. The project is developed in the open on GitHub with 235 stars. Among its 3 catalogued features are Audio Source Separation, ComfyUI Integration, and MelBandRoFormer Architecture.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match