ComfyUI Node
Ideogram 4 Magic Prompt
A ComfyUI node in Eric Prompt Enhancers/Ideogram with 18 inputs and 5 outputs.
Ideogram 4 Magic Prompt
- reference_image
- prompt_json
- high_level
- width
- height
- report
◄idea►
◄application(custom)►
◄backendlm_studio►
◄endpointhttp://localhost:1234/v1►
◄model►
◄temperature1.00►
◄aspect_ratioauto►
◄megapixels1.00►
◄keep_bboxestrue►
◄use_tailoringtrue►
◄max_tokens16384►
◄reference_influencefull►
◄wildcard_seed-1►
◄wildcard_llm_blocktrue►
◄wildcard_instructions—►
◄nsfwoff►
◄violence_filteroff►
CategoryEric Prompt Enhancers/Ideogram
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| idea | STRING | Plain-language idea to expand into an Ideogram 4 caption. | |
| application | COMBO | (custom) | Pick a use case to prefill the idea box with a starter template and steer the expander toward that format. |
| backend | COMBO | lm_studio | 3 options: lm_studio, ollama, qwen3_vl |
| endpoint | STRING | http://localhost:1234/v1 | LM Studio / Ollama base URL. For qwen3_vl, optionally a local model path. |
| model | STRING | Blank = auto-detect the loaded model. | |
| temperature | FLOAT | 1.000–2 | — |
| aspect_ratio | STRING | auto | W:H (e.g. 16:9) or 'auto' to let the model pick. |
| megapixels | FLOAT | 1.000.25–4 | Total output resolution; combined with the aspect ratio to set width/height. |
| keep_bboxes | BOOLEAN | true | Keep element bounding boxes (for the Composer canvas). Off = let Ideogram place freely. |
| use_tailoring | BOOLEAN | true | Apply Eric's documented tailoring addendum on top of the official prompt. See IDEOGRAM_NOTES.md. |
| max_tokens | INT | 163841024–32768 | — |
| reference_imageopt | IMAGE | — | |
| reference_influenceopt | COMBO | full | How a connected reference image guides the caption (needs a vision-capable backend). |
| 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 (5)
| Name | Type | Description |
|---|---|---|
| prompt_json | STRING | — |
| high_level | STRING | — |
| width | INT | — |
| height | INT | — |
| report | STRING | — |