Nodes/ComfyUI-WepeNerd/Local AI Model (Advanced)
ComfyUI Node

Local AI Model (Advanced)

A ComfyUI node in WepeNerd/Local AI/Advanced with 20 inputs and 1 output.

By WepeNerd·Created 4 months ago·Updated 2 days ago· 0
Local AI Model (Advanced)
    • config
    model
    llama_serverauto
    context_size8192
    gpu_layers-1
    target_free_vram_mb24576
    aggressive_vram_handofffalse
    release_after_generatetrue
    mmproj
    startup_timeout_s300
    request_timeout_s600
    extra_server_args
    keep_alive_seconds0
    flash_attn
    cache_type_k
    cache_type_v
    image_min_tokens0
    image_max_tokens0
    cuda_visible_devices
    comfy_vram_handoff
    native_video_max_mb96
    CategoryWepeNerd/Local AI/Advanced

    Inputs (20)

    NameTypeDefaultDescription
    modelCOMBO1 options: <put .gguf models in ComfyUI/models/LLM>
    llama_serverSTRINGauto
    context_sizeINT8192256–262144
    gpu_layersINT-1-1–999
    target_free_vram_mbINT245760–262144
    aggressive_vram_handoffBOOLEANfalse
    release_after_generateBOOLEANtrue
    mmprojoptCOMBO1 options: (none)
    startup_timeout_soptFLOAT3005–1800
    request_timeout_soptFLOAT6005–7200
    extra_server_argsoptSTRING
    keep_alive_secondsoptINT00–86400
    flash_attnoptCOMBO3 options: auto, on, off
    cache_type_koptCOMBO2 options: f16, q8_0
    cache_type_voptCOMBO2 options: f16, q8_0
    image_min_tokensoptINT00–65536
    image_max_tokensoptINT00–65536
    cuda_visible_devicesoptSTRING
    comfy_vram_handoffoptCOMBO3 options: auto, always, never
    native_video_max_mboptINT961–1024

    Outputs (1)

    NameTypeDescription
    configGGUF_LLM_CONFIG