Nodes/FiL_Design_ImageMind/🔌 Provider Loader
ComfyUI Node

🔌 Provider Loader

🔌 FiL Provider Loader — selects an LLM provider, model, and generation parameters. Outputs a `config` dict for downstream FiL nodes.

By FiL-Design-Ai·Created 2 months ago·Updated 16 days ago· 3
🔌 Provider Loader
    • config
    • model
    providerollama
    model(loading...)
    refresh_modelsfalse
    temperature0.70
    max_tokens0
    rate_limit_ms100
    max_image_side1024
    Category🎨 FiL Design/LLM

    Inputs (7)

    NameTypeDefaultDescription
    providerCOMBOollamaChoose where the model runs. Local for offline work, cloud for hosted models.
    modelCOMBO(loading...)Choose which model to use. If the list is empty, refresh it or check the provider account.
    refresh_modelsBOOLEANfalseReload the model list. Use after adding a new model or API key.
    temperatureFLOAT0.700–2Sampling temperature — higher is more creative, lower is more deterministic.
    max_tokensINT00–65536Maximum tokens in the response. 0 = provider default (no explicit limit).
    rate_limit_msINT1000–5000Minimum pause between requests, in milliseconds. On a 429 the pack widens this by itself for a couple of minutes, honouring the provider's own Retry-After when it sends one.
    max_image_sideINT1024128–4096Images are downscaled so their longest side does not exceed this value.

    Outputs (2)

    NameTypeDescription
    configFIL_PROVIDER_CONFIGProvider configuration dict for FiL nodes.
    modelSTRINGNormalised model name string.