ComfyUI Node
Higgs v3 Load Model
Load Higgs Audio v3 TTS natively with ComfyUI/AIMDO memory registration.
Higgs v3 Load Model
- higgs_model
◄modelHiggs Audio v3 TTS 4B - bosonai (auto-download)►
◄dtypeauto►
◄deviceauto►
◄attentionauto►
◄download_if_missingtrue►
CategoryHiggs v3 TTS
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | Higgs Audio v3 TTS 4B - bosonai (auto-download) | Model folder under ComfyUI/models/higgsv3tts. Put model.safetensors in higgs-audio-v3-tts-4b or the root higgsv3tts folder. |
| dtype | COMBO | auto | Weight dtype for Higgs and its audio codec. auto uses bf16 on supported CUDA and fp32 otherwise. fp16 is hidden because it can produce non-finite audio. |
| device | COMBO | auto | Device for native inference. auto follows ComfyUI's current torch device; cuda is fastest; cpu is fallback only and very slow. |
| attention | COMBO | auto | Attention backend. auto/sdpa are usually fastest here; flash_attention needs flash_attn; sageattention may be slower for token-by-token TTS. |
| download_if_missing | BOOLEAN | true | If files are missing, downloads small assets plus the large model.safetensors into ComfyUI/models/higgsv3tts/higgs-audio-v3-tts-4b. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| higgs_model | HIGGSV3TTS_MODEL | — |