Collected sources and patterns will appear here. Add from search or the patterns library.
Image, TextQuestion -> Image
Render text prompts and candidate options directly onto the query image, producing a single image payload.
Problem it solves
Seperated text-image APIs allow models to rely on pre-extracted text/OCR feeds rather than raw visual parsing.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.