ComfyUI Node
Muse Ambient Audio Generator
A ComfyUI node in Muse Collective with 12 inputs and 1 output.
Muse Ambient Audio Generator
- model
- clip
- audio_vae
- base_model
- audio
◄sounds_text►
◄duration_seconds5.0►
◄frame_rate24.00►
◄steps12►
◄cfg1.0►
◄seed42►
◄placeholder_width512►
◄placeholder_height288►
CategoryMuse Collective
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| clip | CLIP | — | |
| audio_vae | VAE | — | |
| sounds_text | STRING | Plain ambient description, or a full prompt containing a [SOUNDS] tag (auto-extracted). | |
| duration_seconds | FLOAT | 5.00.5–60 | — |
| frame_rate | FLOAT | 24.001–120 | — |
| steps | INT | 121–50 | — |
| cfg | FLOAT | 1.00–20 | — |
| seed | INT | 420–18446744073709550000 | — |
| placeholder_width | INT | 51264–2048 | Dummy video-latent size — content is discarded, kept small for speed. |
| placeholder_height | INT | 28864–2048 | — |
| base_modelopt | MODEL | Base model without talking-head LoRA. Connect the UNETLoader output directly here — the LoRA suppresses ambient content. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |