images iWhat to do with pictures in the document. Describe & redraw = the AI looks at each image and makes a clean diagram + caption (uses your Claude plan, or costs money on a paid engine). Reuse cached only = free; only reuses results from an earlier run, never looks again. Skip = ignore images (fastest).

which AI looks at images iThe default is free — it uses your Claude plan. The other two (openrouter, anthropic) charge real money for every image they look at.

preset iStart from a ready-made bundle of settings for a common goal. rag-default = tuned for feeding an AI / search database; plus textbook, flat, archival; qti = Canvas quiz exports (one file per quiz). Anything you change yourself still wins.

tidy the text iHow much to clean up the converted text. off = leave as-is; basic = light tidy; aggressive = also remove more leftover clutter from the original file.

PDF reader iWhich engine reads PDF files. marker is fast; docling is slower but more accurate. Only matters for PDFs.

save each section separately iBesides the one combined file, also save each section of the document as its own separate file.

group sections in folders iWhen saving sections separately, organize them into numbered folders that mirror the document's structure. Needs "save each section separately".

rebuild heading structure iIf a document came out with every heading the same size (common with textbook PDFs), restore the real chapter / sub-section nesting so the structure is correct.

how to rebuild headings iOnly used if "rebuild heading structure" is on. Automatic rules = fast and free. The AI options do a better job (the "reads the whole doc" one is most accurate but costs money). Decide per document picks for you.