Nodes/ComfyUI-H3-Prompt-Creator/H3 Video Prompt Creator
ComfyUI Node

H3 Video Prompt Creator

Automatic H3 T2VA/I2VA/FL2VA/L2VA prompt creator. Connect a first frame, last frame, both, or neither.

By AIJigyasa·Created 11 days ago·Updated 9 days ago· 2
H3 Video Prompt Creator
  • first_frame
  • last_frame
  • h3_prompt
  • reference_analysis
  • generation_notes
idea
duration6.0
extra_instructions
providerOllama (Local)
api_key
api_model
ollama_urlhttp://127.0.0.1:11434
ollama_modelqwen3-vl:8b
temperature0.25
keep_alive10m
request_timeout600
max_output_tokens4096
num_ctx8192
enable_reference_analysistrue
whisper_modelsmall
whisper_deviceauto
enable_audio_transcriptiontrue
CategoryH3 / Prompt Creator

Inputs (19)

NameTypeDefaultDescription
ideaSTRINGThe only creative input you need. The node builds the complete H3 timeline, camera language and audio fields from this idea and any connected frames.
durationFLOAT6.00.1–120Target video duration. Used for final-frame alignment when a last frame is connected.
first_frameoptIMAGEOptional. Connect this to make the node automatically use I2VA (first-frame reference) or FL2VA if a last frame is also connected.
last_frameoptIMAGEOptional. Connect this to make the node automatically use L2VA (last-frame reference) or FL2VA if a first frame is also connected.
extra_instructionsoptSTRINGEverything beyond the main idea is optional. Leave blank and the model will fill in the missing cinematic/audio details itself.
provideroptCOMBOOllama (Local)Ollama (Local) runs on your machine and needs no key. OpenAI, Anthropic, OpenRouter and Google Gemini are hosted APIs and need api_key + api_model. Built-in deterministic skips the model entirely.
api_keyoptSTRINGKey for the hosted providers. Leave blank to read OPENAI_API_KEY, ANTHROPIC_API_KEY, OPENROUTER_API_KEY or GEMINI_API_KEY from the environment — safer, because a key typed here is saved into the workflow JSON and travels with it if you share the workflow.
api_modeloptSTRINGModel for the hosted providers; ignored by Ollama. Blank uses the default: OpenAI gpt-4o, Anthropic claude-opus-5, OpenRouter anthropic/claude-sonnet-5, Gemini gemini-2.0-flash. Must be a vision model when you connect reference images.
ollama_urloptSTRINGhttp://127.0.0.1:11434Ollama server base URL.
ollama_modeloptCOMBOqwen3-vl:8bVision-capable local model, listed from your running Ollama server. Use the Refresh Ollama Models button after pulling a new model.
temperatureoptFLOAT0.250–1.2Lower values improve H3 schema adherence.
keep_aliveoptCOMBO10mKeep the local Ollama model loaded between requests.
request_timeoutoptINT60030–3600Maximum Ollama request time in seconds.
max_output_tokensoptINT4096256–12000Maximum generated tokens. H3 full-reference descriptions benefit from 4096+.
num_ctxoptCOMBO8192Ollama context window. CRITICAL for speed: left unset, Ollama sizes the context from the model maximum (262144 for Qwen3-VL), which needs ~25 GB of KV cache and pushes most layers onto the CPU. 8192 keeps an 8B model fully on a 12 GB GPU. Raise it only when you connect many reference images.
enable_reference_analysisoptBOOLEANtrueRun the separate reference-dossier pass before writing the prompt. Turn off to halve generation time when references are simple.
whisper_modeloptCOMBOsmallLocal faster-whisper model used for dialogue/lyrics transcription. Small is the recommended quality/speed balance.
whisper_deviceoptCOMBOautoDevice for faster-whisper.
enable_audio_transcriptionoptBOOLEANtrueRun faster-whisper when audio is connected (or embedded in the reference video).

Outputs (3)

NameTypeDescription
h3_promptSTRING
reference_analysisSTRING
generation_notesSTRING