ComfyUI Node
FL FishSpeech Model Loader
A ComfyUI node in 🐟FL FishSpeech with 4 inputs and 1 output.
FL FishSpeech Model Loader
- fs_model
◄deviceauto►
◄precisionbfloat16►
◄compilefalse►
◄force_reloadfalse►
Category🐟FL FishSpeech
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| deviceopt | COMBO | auto | Device to load the model on. 'auto' detects GPU automatically. |
| precisionopt | COMBO | bfloat16 | Model precision. bfloat16 recommended for CUDA, float32 for CPU. |
| compileopt | BOOLEAN | false | Enable torch.compile for faster generation. First run will be slow due to compilation. |
| force_reloadopt | BOOLEAN | false | Force reload the model, clearing cache. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| fs_model | FS_MODEL | — |