ComfyUI Node
🕵️ Optic Scanner
👁️ Optic Scanner — analyzes images with LLM vision models and generates optimized prompts for Z-Image, FLUX, SDXL, QWEN, Krea 2, and Ideogram 4.
🕵️ Optic Scanner
- config
- image
- prompt
- metadata_json
- metadata_dict
◄agent⚪ None►
◄agent_focus⚪ None►
◄detail_levelnormal►
◄languageen►
◄model_typeAuto/None►
◄video_duration0►
◄video_aspectAuto►
◄video_soundAuto►
◄video_cameraAuto►
◄prompt_modeAuto►
◄photo_styleNone►
◄nsfw_photo_styleNone►
◄art_styleNone►
◄nsfw_art_styleNone►
◄seed-1►
◄response_formattext►
◄width0►
◄height0►
◄prompt►
◄negative_prompt►
◄custom_style►
Category🎨 FiL Design/LLM
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| config | FIL_PROVIDER_CONFIG | Settings received from the Loader node. | |
| agent | COMBO | ⚪ None | Subject domain — what is in the frame. |
| agent_focus | COMBO | ⚪ None | Craft layer to weigh heavier on top of the agent: composition, light, fine detail, cinematic read, or the subject's state and movement. |
| detail_level | COMBO | normal | How detailed the answer should be. |
| language | COMBO | en | Language of the answer. Auto replies in the language of your prompt. |
| model_type | COMBO | Auto/None | Target generation model — adjusts prompt syntax, length, and format. Video is a universal profile for video models (MiniMax H2/H3, Wan, HunyuanVideo, LTX Video, Kling); MiniMax H3 gets a dedicated timeline shot-block profile. |
| video_duration | INT | 00–20 | Requested clip length in seconds. 0 = Auto (the LLM decides). The range follows the model: MiniMax H3 accepts 4-15 whole seconds (API limit), universal Video 2-20. Shown only for video model types. |
| video_aspect | COMBO | Auto | Aspect ratio written into the shot framing — for MiniMax H3 into the timeline header line ('10s, 16:9.'). Auto leaves the choice to the LLM. Shown only for video model types. |
| video_sound | COMBO | Auto | Sound design mode. Auto = the LLM decides; Off = silent clip (no sound clause); Layered = mandatory ambience + foley + music clause for audio-capable models (H3, Veo). Shown only for video model types. |
| video_camera | COMBO | Auto | Preferred camera move. The LLM builds the shot around it and may adapt per story stage — a preference, not a hard lock. Shown only for video model types. |
| prompt_mode | COMBO | Auto | Auto picks Hybrid or Two-Stage depending on whether a style is selected. |
| photo_style | COMBO | None | Photographic style overlay applied on top of the base description. |
| nsfw_photo_style | COMBO | None | Adult-only photographic style overlay (alternative to Photo style). |
| art_style | COMBO | None | Art style overlay applied on top of the base description. |
| nsfw_art_style | COMBO | None | Adult-only art style overlay (alternative to Art style). |
| seed | INT | -1-1–999999999999 | Provider-side generation seed, if supported. -1 lets the provider pick one. |
| response_format | COMBO | text | Output shape: prose text, flat comma-separated tags, or a JSON object. |
| imageopt | IMAGE | Image or batch to analyze. Leave disconnected to generate from Prompt field. | |
| widthopt | INT | 00–16384 | Target image width in pixels. Helps tailor prompt composition to aspect ratio if > 0. |
| heightopt | INT | 00–16384 | Target image height in pixels. Helps tailor prompt composition to aspect ratio if > 0. |
| promptopt | STRING | WITHOUT AN IMAGE — the idea itself, expanded into a finished prompt: ginger cat on a windowsill, rain outside abandoned metro station, morning light through a hole in the ceiling WITH AN IMAGE — what to focus on and what the text is for: emphasise the light and skin texture prompt for an album cover the cup on the table is the subject, not the person keep empty space on the right for a headline WON'T WORK (this comes from the image): replace the woman with a man make her stand instead of sit remove the second person Leave empty and the image is simply described in detail. Details: docs/scanner-prompts.md | |
| negative_promptopt | STRING | Removes WORDS from the generated text, not objects from the image. Pose, subject and composition cannot be changed here — use the prompt field. PUT HERE what the model adds on its own: cliches: masterpiece, best quality, 8k, highly detailed effects: bokeh, lens flare, dramatic vignette junk: watermark, logo, signature, text overlay defects: extra fingers, plastic skin, waxy texture judgements: beautiful, stunning, breathtaking Short nouns, comma-separated, 5-10 of them. Not sentences with 'no': under FLUX / Z-Image Turbo / Krea 2 / Ideogram 4 / Video the list is flipped into positive wording, and 'do not make it blurry' has nothing to flip — write blurry. Not sure what to put? Leave it empty, run once, and pick out the words that bother you in the answer. Details: docs/scanner-prompts.md | |
| custom_styleopt | STRING | Custom style text. Overrides photo/art/nsfw preset styles. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | Generated prompt text. |
| metadata_json | STRING | JSON metadata string. |
| metadata_dict | DICT | Parsed metadata dict. |