Nodes/Artha-Gemini/🔱 Gemini Condense
ComfyUI Node

🔱 Gemini Condense

Gemini Question node condenses a propt to a target word count preserving the concept.

By Cyrostar·Created about a year ago·Updated 12 months ago· 1
🔱 Gemini Condense
    • response
    â—„text_promptâ–º
    â—„max_words400â–º
    â—„api_keyâ–º
    â—„modelgemini-2.5-flashâ–º
    â—„max_tokens5000â–º
    â—„temperature0.7â–º
    CategoryArtha/LLM/GEMINI

    Inputs (6)

    NameTypeDefaultDescription
    text_promptSTRING—
    max_wordsINT4001–10000For Gemini models, a token is equivalent to about 4 characters. 100 tokens is equal to about 60-80 English words.
    api_keySTRINGAPI key will be visible in plain text. Consider adding your api to the api.json located inside this custom node folder.
    modelCOMBOgemini-2.5-flash5 options: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.0-flash, gemini-2.0-flash-lite
    max_tokensINT50001–8192For Gemini models, a token is equivalent to about 4 characters. 100 tokens is equal to about 60-80 English words.
    temperatureFLOAT0.70–2A temperature of 0 means only the most likely tokens are selected, and there's no randomness. Conversely, a high temperature injects a high degree of randomness into the tokens selected by the model, leading to more unexpected, surprising model responses.

    Outputs (1)

    NameTypeDescription
    responseSTRING—