Nodes/ComfyUI-Raon-OpenTTS/Raon OpenTTS Load Model
ComfyUI Node

Raon OpenTTS Load Model

Load Raon-OpenTTS (0.3B or 1B) natively with ComfyUI/AIMDO memory registration.

By Saganaki22·Created 6 days ago·Updated 6 days ago· 11
Raon OpenTTS Load Model
    • raon_model
    weightsRaon-OpenTTS-1B-int8-convrot.safetensors
    dtypeauto
    deviceauto
    attentionauto
    download_if_missingtrue
    CategoryRaonOpenTTS

    Inputs (5)

    NameTypeDefaultDescription
    weightsCOMBORaon-OpenTTS-1B-int8-convrot.safetensorsCheckpoint file from ComfyUI/models/raon_opentts (0.3B and 1B in separate folders). int8-convrot is the quantized build (smallest, runs through comfy-kitchen INT8 kernels); bf16 is the half-precision reference. The fp32 extraction is conversion reference only and is not listed. With download_if_missing on, only the selected build (plus its config/vocab and the vocoder) is downloaded — never the whole repo.
    dtypeCOMBOautoCompute/storage dtype for the DiT. auto picks bf16 on supported GPUs. INT8 weights always stay INT8 and their scales fp32 regardless of this choice.
    deviceCOMBOautoDevice for inference. auto follows ComfyUI's current torch device; cpu is a slow fallback.
    attentionCOMBOautoAttention backend for the DiT blocks. auto uses flash_attn (FA2) when installed with half-precision compute, otherwise torch SDPA. sageattention patches SDPA at generation time.
    download_if_missingBOOLEANtrueDownload the HiFi-GAN vocoder into ComfyUI/models/raon_opentts when missing.

    Outputs (1)

    NameTypeDescription
    raon_modelRAON_OPENTTS_MODEL