Nodes/ComfyUI_Simple_Qwen3-VL-gguf/LLM Sampling Config
ComfyUI Node

LLM Sampling Config

A ComfyUI node in 🌐 SimpleQwenVL with 11 inputs and 1 output.

By KLL535Β·Created 9 months agoΒ·Updated about a month agoΒ· 80
LLM Sampling Config
    • config
    β—„max_tokens2048β–Ί
    β—„temperature0.70β–Ί
    β—„top_p0.95β–Ί
    β—„min_p0.05β–Ί
    β—„top_k40β–Ί
    β—„repeat_penalty1.10β–Ί
    β—„presence_penalty0.0β–Ί
    β—„frequency_penalty0.0β–Ί
    β—„image_min_tokens0β–Ί
    β—„image_max_tokens0β–Ί
    β—„config_overrideβ€”β–Ί
    Category🌐 SimpleQwenVL

    Inputs (11)

    NameTypeDefaultDescription
    max_tokensINT204816–32768Max output tokens. Thinking models need 4096+.
    temperatureFLOAT0.700–20.1=focused, 0.7=balanced, 1.2+=creative. Lower = more deterministic.
    top_pFLOAT0.950–1Nucleus sampling: cumulative probability cutoff. Lower = more focused.
    min_pFLOAT0.050–1Cut off tokens with prob < min_p * (top_token_prob). Great for reducing garbage.
    top_kINT400–500Limit to top-K tokens. 0 = disabled. Good for strict output.
    repeat_penaltyFLOAT1.101–2Penalty for repeating tokens. >1.0 discourages loops.
    presence_penaltyFLOAT0.0-2–2Penalize tokens that appeared at all. >0 encourages new topics.
    frequency_penaltyFLOAT0.0-2–2Penalize tokens by frequency. >0 reduces repetition of common words.
    image_min_tokensINT00–8192Min tokens for image embedding. 0 = not set
    image_max_tokensINT00–16384Max tokens for image embedding. 0 = not set
    config_overrideoptSTRINGβ€”

    Outputs (1)

    NameTypeDescription
    configSTRINGβ€”