ComfyUI Node
H3 Video Prompt Creator
Automatic H3 T2VA/I2VA/FL2VA/L2VA prompt creator. Connect a first frame, last frame, both, or neither.
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)
| Name | Type | Default | Description |
|---|---|---|---|
| idea | STRING | The only creative input you need. The node builds the complete H3 timeline, camera language and audio fields from this idea and any connected frames. | |
| duration | FLOAT | 6.00.1–120 | Target video duration. Used for final-frame alignment when a last frame is connected. |
| first_frameopt | IMAGE | Optional. Connect this to make the node automatically use I2VA (first-frame reference) or FL2VA if a last frame is also connected. | |
| last_frameopt | IMAGE | Optional. Connect this to make the node automatically use L2VA (last-frame reference) or FL2VA if a first frame is also connected. | |
| extra_instructionsopt | STRING | Everything beyond the main idea is optional. Leave blank and the model will fill in the missing cinematic/audio details itself. | |
| provideropt | COMBO | Ollama (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_keyopt | STRING | Key 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_modelopt | STRING | Model 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_urlopt | STRING | http://127.0.0.1:11434 | Ollama server base URL. |
| ollama_modelopt | COMBO | qwen3-vl:8b | Vision-capable local model, listed from your running Ollama server. Use the Refresh Ollama Models button after pulling a new model. |
| temperatureopt | FLOAT | 0.250–1.2 | Lower values improve H3 schema adherence. |
| keep_aliveopt | COMBO | 10m | Keep the local Ollama model loaded between requests. |
| request_timeoutopt | INT | 60030–3600 | Maximum Ollama request time in seconds. |
| max_output_tokensopt | INT | 4096256–12000 | Maximum generated tokens. H3 full-reference descriptions benefit from 4096+. |
| num_ctxopt | COMBO | 8192 | Ollama 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_analysisopt | BOOLEAN | true | Run the separate reference-dossier pass before writing the prompt. Turn off to halve generation time when references are simple. |
| whisper_modelopt | COMBO | small | Local faster-whisper model used for dialogue/lyrics transcription. Small is the recommended quality/speed balance. |
| whisper_deviceopt | COMBO | auto | Device for faster-whisper. |
| enable_audio_transcriptionopt | BOOLEAN | true | Run faster-whisper when audio is connected (or embedded in the reference video). |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| h3_prompt | STRING | — |
| reference_analysis | STRING | — |
| generation_notes | STRING | — |