Nodes/Comfyui-Z-Image-Utilities/Z-Image API Config
ComfyUI Node

Z-Image API Config

Configure LLM API connection. Supports OpenRouter, local servers, and direct HuggingFace model loading.

By Koko-boya·Created 9 months ago·Updated 5 months ago· 127
Z-Image API Config
    • config
    provideropenrouter
    modelqwen/qwen3-235b-a22b:free
    api_key
    local_endpointhttp://localhost:11434/v1
    llm_path
    auto_download_fallbackfalse
    quantization4bit
    deviceauto
    CategoryZ-Image

    Inputs (8)

    NameTypeDefaultDescription
    providerCOMBOopenrouterSelect API provider: openrouter (cloud), local (API server), or direct (HuggingFace model loading)
    modelSTRINGqwen/qwen3-235b-a22b:freeModel identifier. OpenRouter: provider/model-name | Local: model name from server | Direct: HuggingFace repo ID
    api_keyoptSTRINGAPI key for OpenRouter. Get one at https://openrouter.ai/keys
    local_endpointoptSTRINGhttp://localhost:11434/v1Local LLM server endpoint (Ollama: 11434, LM Studio: 1234, vLLM: 8000)
    llm_pathoptSTRINGCustom path to local LLM models. If set, model name is treated as folder name. If empty, downloads from HuggingFace.
    auto_download_fallbackoptBOOLEANfalseIf enabled: try manual path first, fall back to auto-download if not found. If disabled: manual path is strict (fails if not found).
    quantizationoptCOMBO4bitModel precision. 4-bit saves VRAM, 8-bit is balanced, FP16/None gives best quality
    deviceoptCOMBOautoDevice for direct model loading

    Outputs (1)

    NameTypeDescription
    configZIMAGE_CONFIG