image-gate-by-text — Conditional AI Model
A gate: the image passes only if an accompanying text input matches your condition, and otherwise nothing is emitted and the rest of the branch is skipped. Wire a classifier into it to build a conditional flow.
Details
- CategoryConditional
- Year-1
- License
Inputs & Outputs
- ImageInputimage
The input image
- TextInputstring
The input text (can be the result of classification)
- ImageOutputimage
Image passed through if text condition is met
Parameters
- gate_conditionstringdefault
Text to match against
The reference string to compare the incoming text against. How the comparison happens is controlled by `method`. Leave blank to let everything through.
- methodstringdefault Matchedoptions: Matched w/ Case, Matched w/o Case, Contained w/ Case, +1 more
Matching method
How to compare. 'Matched w/ Case' = exact equality. 'Matched w/o Case' = case-insensitive equality. 'Contained w/ Case' = case-sensitive substring. 'Contained w/o Case' = case-insensitive substring. Pick 'Contained w/o Case' when matching against free-form text like classifier output or LLM-generated labels.
Tags
Alternatives in Selection & Extraction
- Color Pick by Class
Extract a segmentation class by name.
- Color Pick by RGB Value
Extract segmentation regions by exact RGB color.
- Image Collect
Gather separately made images into one image list, in port order.
- Image Crop by Class
Crop detected objects by class name.
- Image Crop by Coord
Crop a region from explicit bounding-box coordinates.
- Image Crop Each by Class
Crop every detected object into its own image.
- Image Selector
Pick first non-empty image from inputs (fallback).
- List Extract
Extract one image from an image list by index.