Nodes/ComfyUI-RH-daVinci-MagiHuman/RH MagiHuman Model Loader
ComfyUI Node

RH MagiHuman Model Loader

A ComfyUI node in MagiHuman with 5 inputs and 1 output.

By RH-RunningHub·Created 7 days ago·Updated 7 days ago· 0
RH MagiHuman Model Loader
    • pipeline
    model_type
    use_turbo_vaetrue
    vram_modemid_vram
    sr_modelnone
    torch_compilefalse
    CategoryMagiHuman

    Inputs (5)

    NameTypeDefaultDescription
    model_typeCOMBO2 options: base, distill
    use_turbo_vaeBOOLEANtrue
    vram_modeCOMBOmid_vrammid_vram: INT8 DiT + GPU/CPU ping-pong (~16 GB). low_vram: INT8 DiT + layer-by-layer CPU offload (~6.5 GB base).
    sr_modelCOMBOnoneSuper-resolution model. Upscales base output to 540p or 1080p in a second denoising pass.
    torch_compileBOOLEANfalseEnable torch.compile (dynamo). First run compiles ~5 min, subsequent runs faster. Disable for eager mode.

    Outputs (1)

    NameTypeDescription
    pipelineMAGIHUMAN_PIPELINE