raubatz/comfyui-custom-nodes / comfyui-multigpu /web /docs /MMAudioModelLoaderMultiGPU.md
raubatz's picture
|
download
raw
802 Bytes
# MMAudioModelLoaderMultiGPU
`MMAudioModelLoaderMultiGPU` loads MMAudio diffusion checkpoints while letting you pin the model weights to a specific compute device. Use it to keep long-running audio generations off your primary image GPU.
## Inputs
### Required
| Parameter | Data Type | Description |
| --- | --- | --- |
| `mmaudio_model` | `STRING` | Model filename from `ComfyUI/models/mmaudio`. |
| `base_precision` | `STRING` | Weight precision to request (`fp16`, `fp32`, `bf16`). |
### Optional
| Parameter | Data Type | Description |
| --- | --- | --- |
| `device` | `STRING` | Target device for the loaded model (e.g. `cuda:0`, `cpu`). |
## Outputs
| Output Name | Data Type | Description |
| --- | --- | --- |
| `mmaudio_model` | `MMAUDIO_MODEL` | Loaded MMAudio diffusion pipeline. |

Xet Storage Details

Size:
802 Bytes
·
Xet hash:
f74fc121aac1e89868049f198a0a8ea1037385532f34f6437d608bcf17330489

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.