Nodes/ComfyUI Lackluster Nodes/Lackluster Prompt Enhancer
ComfyUI Node

Lackluster Prompt Enhancer

A ComfyUI node in Lackluster/Prompt with 18 inputs and 2 outputs.

By LacklusterOpsec·Created 4 months ago·Updated 28 days ago· 0
Lackluster Prompt Enhancer
  • image0
  • image1
  • image2
  • image3
  • image4
  • enhanced_prompt
  • negative_prompt
prompt
task_typev2v
ollama_urlhttp://127.0.0.1:11434
ollama_model
api_formatOllama
auto_enhancefalse
text_input
negative_prompt
temperature0.70
max_tokens2048
seed0
prepend_system_prompttrue
unload_ollamafalse
CategoryLackluster/Prompt

Inputs (18)

NameTypeDefaultDescription
promptSTRINGRaw instruction or generation prompt. Use the Enhance button or enable auto-enhance to rewrite with the task template.
task_typeCOMBOv2vBernini task mode. Determines the enhancement template and system prompt used by the LLM.
ollama_urlSTRINGhttp://127.0.0.1:11434LLM endpoint URL (Ollama or vLLM/OpenAI-compatible).
ollama_modelSTRINGLLM model name. Leave empty to skip enhancement (pass-through).
api_formatCOMBOOllamaOllama uses /api/chat. OpenAI/vLLM uses /v1/chat/completions.
auto_enhanceBOOLEANfalseWhen enabled, enhances the prompt server-side on every queue.
image0optIMAGEReference image slot 0 = 'image0' in your prompt. Converted to base64 and sent to multimodal LLMs.
image1optIMAGEReference image slot 1. Use 'image1' in your prompt.
image2optIMAGEReference image slot 2. Use 'image2' in your prompt.
image3optIMAGEReference image slot 3. Use 'image3' in your prompt.
image4optIMAGEReference image slot 4. Use 'image4' in your prompt.
text_inputoptSTRINGText node connection input. If connected, replaces the prompt field.
negative_promptoptSTRINGCustom negative prompt. Leave empty to use Bernini's default.
temperatureoptFLOAT0.700–2LLM temperature. Lower = more deterministic. GPT-5 / o-series models ignore this and use their internal default.
max_tokensoptINT204864–8192Maximum tokens in the LLM response.
seedoptINT00–2147483647LLM seed for reproducibility. 0 = random. Ollama only; ignored by OpenAI/vLLM endpoints.
prepend_system_promptoptBOOLEANtruePrepend the task system prompt to the enhanced output. Useful for CLIPTextEncode / T5 conditioning.
unload_ollamaoptBOOLEANfalseTell Ollama to unload the model from VRAM after enhancement.

Outputs (2)

NameTypeDescription
enhanced_promptSTRING
negative_promptSTRING