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

H3 Full-Reference Video Prompt Creator

Multimodal H3 full-reference prompt creator with IMAGE, VIDEO and AUDIO inputs, Qwen3-VL reasoning, faster-whisper transcription and librosa/FFmpeg audio analysis.

By AIJigyasa·Created 11 days ago·Updated 9 days ago· 2
H3 Full-Reference Video Prompt Creator
  • reference_video
  • reference_audio
  • reference_image_1
  • reference_image_2
  • reference_image_3
  • reference_image_4
  • reference_image_5
  • reference_image_6
  • h3_prompt
  • reference_analysis
  • audio_analysis
  • generation_notes
idea
target_duration6.0
reference_intentAuto
reference_notes
audio_transcript_or_notes
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 (27)

NameTypeDefaultDescription
ideaSTRINGSimple target idea. The node uses it together with any connected reference images, video and audio to write the complete six-section H3 full-reference prompt.
target_durationFLOAT6.00.1–120Target duration used to shape the generated timeline. If reference video duration is available, Ollama also receives it as evidence.
reference_videooptVIDEOOptional full reference video. Sampled frames are sent to Ollama; the source is represented as <Video 1> in the H3 prompt.
reference_audiooptAUDIOOptional reference audio. Local faster-whisper transcribes speech/lyrics and librosa extracts audio/music features; exact user notes can override ambiguity.
reference_image_1optIMAGEOptional picture reference 1. Automatically represented as <Picture 1> unless Ollama determines another H3 reference role.
reference_image_2optIMAGEOptional picture reference 2.
reference_image_3optIMAGEOptional picture reference 3.
reference_image_4optIMAGEOptional picture reference 4.
reference_image_5optIMAGEOptional picture reference 5.
reference_image_6optIMAGEOptional picture reference 6.
reference_intentoptCOMBOAutoOptional hint. Auto is recommended: the node infers the task type from the connected references and notes.
reference_notesoptSTRINGOptional clarification. Leave blank when the references and simple idea are self-explanatory.
audio_transcript_or_notesoptSTRINGOllama itself is not assumed to hear arbitrary AUDIO tensors. Put exact lyrics/dialogue here when they must be preserved verbatim.
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 (4)

NameTypeDescription
h3_promptSTRING
reference_analysisSTRING
audio_analysisSTRING
generation_notesSTRING