Generate full music tracks from text prompts in ComfyUI with Ace-Step 1.5. One model file.
Audio & Music
Audio & Music
Generate full music tracks and audio from text prompts. Local generation, no API keys.
ComfyUI Audio & Music Workflows
Generate complete music tracks and audio from text prompts in ComfyUI. These audio workflows run diffusion models tuned for sound: describe a genre, mood, and instrumentation in plain language and the model produces a full mixed track, ready to export. Each template is a ready-to-run node graph you can load directly into ComfyUI. Browse the audio and music templates below.