Stable Audio 2.5: Audio to Audio
Transform audio into new compositions using Stable Audio 2.5. Upload audio and AI creates complete tracks.
About
This ComfyUI workflow, titled 'Stable Audio 2.5: Audio to Audio', is designed to transform existing audio into new compositions using the Stable Audio 2.5 model. It leverages several nodes, including LoadAudio, RecordAudio, and StabilityAudioToAudio, to facilitate the seamless conversion of audio inputs into creatively altered outputs. Users can either upload pre-existing audio files using the LoadAudio node or record new audio directly through the RecordAudio node. The StabilityAudioToAudio node is the core of this workflow, applying advanced AI techniques to reinterpret the audio input into a novel composition.
What you provide
- Reading the workflow
Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.
Try in CloudQuestions & answers
You can upload audio files in common formats such as MP3 or WAV using the LoadAudio node.
The transformation strength determines how much the output differs from the input. Lower strength values result in outputs more similar to the original audio.
Yes, you can use the RecordAudio node to capture live audio directly into the workflow for immediate transformation.
Ensure that the audio duration matches the capabilities of the StabilityAudioToAudio node for optimal results. Longer durations may require adjustments.