Nodes/Prompt808/Generate Prompt
ComfyUI Node

Generate Prompt

Generates prompts from your Prompt808 library. All settings are exposed as node inputs. Debug mode is in ComfyUI Settings > Prompt808.

By Machete3000·Created 6 months ago·Updated 4 months ago· 2
Generate Prompt
  • libraries
  • prompt
  • negative_prompt
  • status
library(no libraries)
prompt_typeAny
archetypeAny
archetype_influence70
moodAny
llm_modelNone
enrichmentAny
quantizationFP16
temperature0.70
max_tokens1024
api_urlhttp://127.0.0.1:1234
keep_model_loadedfalse
prefix
suffix
seed0
CategoryPrompt808

Inputs (16)

NameTypeDefaultDescription
librariesoptP808_LIBRARIESConnect a Library Select node for multi-library generation
libraryoptCOMBO(no libraries)No libraries — open the Prompt808 sidebar (camera icon) to create one
prompt_typeoptCOMBOAnyPrompt style (Cinematic, Documentary, etc.)
archetypeoptCOMBOAnyArchetype to filter elements by
archetype_influenceoptINT700–100How strongly the selected archetype biases element selection (0-100%). Controls two things: (1) per-category probability of picking an archetype-matched element vs. a random pool element, and (2) minimum inclusion rate for categories the archetype covers -- e.g. a pose-only archetype at 80% guarantees poses appear in at least 80% of prompts. At 100%, ONLY archetype-matched categories are included. Has no effect when archetype is None.
moodoptCOMBOAnyMood modifier for the generated prompt
llm_modeloptCOMBONoneLLM model for prompt composition. API (recommended) = OpenAI-compatible server (LM Studio, Ollama, llama.cpp, vLLM) at the api_url below — typically 10-20x faster than the local HF path on the same GPU. None = simple mode (no LLM). The other entries are local HF models — useful for self-contained installs but slower than a llama.cpp/GGUF backend.
enrichmentoptCOMBOAnyCreative enrichment level for LLM composition
quantizationoptCOMBOFP16LLM quantization (FP16, FP8, 8-bit, 4-bit)
temperatureoptFLOAT0.700.1–1.5LLM sampling temperature (higher = more creative)
max_tokensoptINT1024128–2048Maximum tokens for LLM generation
api_urloptSTRINGhttp://127.0.0.1:1234Server URL for API mode (used when llm_model is set to API). Works with LM Studio, Ollama, llama.cpp, vLLM, or any OpenAI-compatible endpoint. Default points to LM Studio's local server. Ignored when using a local HF model.
keep_model_loadedoptBOOLEANfalseKeep LLM offloaded to CPU RAM after generation (faster next run)
prefixoptSTRINGText prepended to the generated prompt (e.g. LoRA trigger word)
suffixoptSTRINGText appended to the generated prompt (e.g. quality tags)
seedoptINT00–4294967295Random seed for deterministic generation

Outputs (3)

NameTypeDescription
promptSTRINGGenerated prompt
negative_promptSTRINGNegative prompt (terms to avoid)
statusSTRINGGeneration status and archetype used