Nodes/Vsaan212-workflow-utilities/LazyPrompt — Prompt Engineer
ComfyUI Node

LazyPrompt — Prompt Engineer

A ComfyUI node in vsaan212/LazyPrompt with 25 inputs and 3 outputs.

By vsaan212·Created 9 months ago·Updated about a month ago· 2
LazyPrompt — Prompt Engineer
  • image
  • PROMPT
  • PREVIEW
  • NEG_PROMPT
bypassfalse
user_inputa woman walks through a rain-soaked city street at night
target_model🎬 LTX 2.3 — video, cinematic arc + audio
environmentNone — LLM decides
screenplay_modefalse
creativity0.9 - Balanced Professional
seed-1
invent_dialoguetrue
keep_model_loadedfalse
offline_modefalse
video_length8.00
fps0
env_seed0
modelLM Studio (API)
local_path_8b
local_path_3b
lm_studio_model
lm_studio_ttl5
max_output_tokens900
system_prompt
scene_context
lora_triggers
character
prompt_override_input
Categoryvsaan212/LazyPrompt

Inputs (25)

NameTypeDefaultDescription
bypassBOOLEANfalseWhen ON, skips the LLM entirely and sends your text straight through. Use for manual prompts or testing.
user_inputSTRINGa woman walks through a rain-soaked city street at nightRough idea, sentence, or numbered steps. The LLM expands into a prompt for the selected target model.
target_modelCOMBO🎬 LTX 2.3 — video, cinematic arc + audioPrompt style: LTX / Wan (video), Flux / SDXL / Pony / SD 1.5 (image). "None" = no JSON template (empty system unless override). Default templates load from lazyprompt/system_prompts.json (restart or R to reload after edits).
environmentCOMBONone — LLM decidesInjects location, lighting, and (for video) sound. Random uses env_seed.
screenplay_modeBOOLEANfalseLTX 2.3 only: screenplay-style character/scene/beats. Ignored for other targets.
creativityCOMBO0.9 - Balanced ProfessionalSampling temperature preset for local HF models and LM Studio.
seedINT-1-1–2147483647LLM seed. -1 = random each run.
invent_dialogueBOOLEANtrueVideo targets: when ON, invent inline dialogue; when OFF, only quoted user dialogue or silence.
keep_model_loadedBOOLEANfalseKeep the local HF model in VRAM between runs. Off frees VRAM after each run.
offline_modeBOOLEANfalseON = no HuggingFace network; local cache / paths only.
video_lengthFLOAT8.000.25–300Video duration in seconds (video targets). Frame count for hints = length × fps. Image targets ignore this.
fpsINT00–600 = auto from target model (Wan 16, LTX 25, else 24). Set >0 to override.
env_seedINT00–2147483647Seed when environment is Random. 0 = different pick each run.
modelCOMBOLM Studio (API)Backend LLM: local HF checkpoints or LM Studio REST API (native /api/v1/chat with OpenAI fallback).
local_path_8bSTRINGOptional local snapshot path for the 8B model.
local_path_3bSTRINGOptional local snapshot path for the 3B model.
lm_studio_modelSTRINGRequired when model is LM Studio (API). LM Studio 0.4+ uses /api/v1/chat; older versions fall back to /v1/chat/completions.
lm_studio_ttlINT50–3600LM Studio JIT unload: when > 0, unloads the model immediately after each run via /api/v1/models/unload (v1 chat). On OpenAI fallback only, also sends idle TTL in the request body. 0 = leave loaded.
max_output_tokensINT90096–16000Hard cap on completion length (HF max_new_tokens / LM Studio max_tokens). The pacing hint asks the model for ~one-third of this many tokens by default — raise both together for longer prompts (e.g. 1500 max → ~500 target).
system_promptSTRINGOverride system prompt. If empty, uses lazyprompt/system_prompts.json for the selected target. When target is None and this field has text, only that text is used as system prompt and the user message is scene + idea only (no auto augmentation). Default templates load from lazyprompt/system_prompts.json (restart or R to reload after edits).
scene_contextoptSTRINGAuthoritative scene/subject text from the vision node or manual paste.
lora_triggersoptSTRINGInjected so the model places these words at the very start of the output.
characteroptSTRINGSubject / character description — always prepended to the LLM user message (including minimal mode and when prompt_override_input is set). Wire from Lazy-subject-and-scene-automation subject_description.
imageoptIMAGEOptional. For use with LM Studio (API) and a vision-enabled model loaded in LM Studio. Sends this frame as an image alongside your text (OpenAI-style multimodal chat). Ignored when using local Hugging Face text-only models — use LazyPrompt — Vision Describe + scene_context instead.
prompt_override_inputoptSTRINGWhen connected/non-empty, replaces user_input for the LLM request (LM Studio API and local HF). Wire from Lazy-subject-and-scene-automation prompt_override.

Outputs (3)

NameTypeDescription
PROMPTSTRING
PREVIEWSTRING
NEG_PROMPTSTRING