ComfyUI Node
Alice T2V Prompt Refiner
A ComfyUI node in Eric Prompt Enhancers with 17 inputs and 3 outputs.
Alice T2V Prompt Refiner
- image
- refined_prompt
- image_description
- status
◄backendlm_studio►
◄endpointhttp://localhost:1234/v1►
◄model_pathH:\Captioning\Qwen3-VL-8B-Instruct-abliterated-v2.0.Q8_0.gguf►
◄mmproj_pathH:\Captioning\Qwen3-VL-8B-Instruct-abliterated-v2.0.mmproj-f16.gguf►
◄text_prompt►
◄style_presetcinematic►
◄custom_style_notes►
◄temperature0.70►
◄max_tokens512►
◄show_thinkingfalse►
◄custom_system_prompt►
◄wildcard_seed-1►
◄wildcard_llm_blocktrue►
◄wildcard_instructions—►
◄nsfwoff►
◄violence_filteroff►
CategoryEric Prompt Enhancers
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| backend | COMBO | lm_studio | lm_studio: calls http://localhost:1234/v1 (OpenAI-compatible). ollama: calls http://localhost:11434. |
| endpoint | STRING | http://localhost:1234/v1 | API endpoint URL. |
| model_path | STRING | H:\Captioning\Qwen3-VL-8B-Instruct-abliterated-v2.0.Q8_0.gguf | REMINDER - load this GGUF in LM Studio before running. Not used directly by the node. |
| mmproj_path | STRING | H:\Captioning\Qwen3-VL-8B-Instruct-abliterated-v2.0.mmproj-f16.gguf | REMINDER - load this mmproj alongside the GGUF in LM Studio for vision support. |
| text_prompt | STRING | Rough idea for the video. Leave empty for image-only mode. | |
| style_preset | COMBO | cinematic | 7 options: cinematic, nature_documentary, portrait_character, architecture_urban, action_dynamic, abstract_artistic, +1 |
| custom_style_notes | STRING | Used only when style_preset = 'custom'. | |
| temperature | FLOAT | 0.700.1–1.5 | — |
| max_tokens | INT | 512128–1024 | — |
| show_thinking | BOOLEAN | false | Print Qwen3 reasoning chain to console. Also enables detailed response debug logging. |
| imageopt | IMAGE | Optional reference image. Requires a vision model in LM Studio. | |
| custom_system_promptopt | STRING | Fully overrides the built-in system prompt when non-empty. | |
| wildcard_seedopt | INT | -1-1–2147483647 | Seed for wildcards: __name__, {a|b|c}, __objects[tag AND tag]__. -1 = fresh roll every run. 0 or more = reproducible picks. |
| wildcard_llm_blockopt | BOOLEAN | true | Tell the LLM which elements were picked at random so it keeps them: concepts keep their meaning, __=verbatim__ picks stay word for word. Off = the LLM only sees the resolved text. |
| wildcard_instructionsopt | STRING | Connect the llm_instructions output of a Wildcard Processor or Semantic Variation node here when the wildcards were resolved before this node. The LLM is then told which elements were picked at random, and verbatim picks are checked in its answer, exactly as if this node had resolved them itself. | |
| nsfwopt | COMBO | off | How far wildcard picks may go (a word match on each entry and on list names, no model). off = SFW: no suggestive, nude or explicit lists or entries suggestive = also lingerie, bikinis, sexy, seductive ... nudity = also nude, naked, topless ... explicit = everything, including lists under _nsfw/ Fix a wrong rating in _catalog_user.yaml (nsfw: on a list, ratings: on entries). Entries pairing minor-related and sexual terms are removed at every level (config.json "content_filter"). |
| violence_filteropt | COMBO | off | Hold back violent wildcard picks (a word match on each entry and on list names, no model). off = nothing held back no gore = blood and gore, torture, mutilation, corpses no gore or violent acts = also murder, execution, stabbing, strangling, suicide ... no violence or weapons = also guns, swords, knives, bombs, battle, war Only wildcard picks are filtered; text you type is left as is. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| refined_prompt | STRING | — |
| image_description | STRING | — |
| status | STRING | — |