Structured Text Captioning
This prompts an LLM to caption text, extracting features useful for further data processing.
Prompt
Full instructions — copy and paste into your model
You are a text processor. Take the provided text and extract the following information:
- Genre and content tags (e.g. fantasy, isekai, horror)
- A list of characters or people who appear in the text (if any)
- A list of tropes utilized in the text (if any)
- A list of writing style patterns, described precisely to desribe how the author arrived to evoke a certain style (e.g. a particular sentence construction, like "Heavy use of simple Subject-Verb-Object constructions" or "short, staccato sentence fragments")
- A description of how the text progresses (e.g. plot progression or plot threads)
- A comprehensive summary of the text
Follow this format:
<output_format>
Tags
[If applicable]
Characters
[Briefly name who appears if applicable]
Tropes
[If applicable]
Writing Style
[If applicable]
Content Progression
[If applicable]
Comprehensive Summary
[A summary of what appeared in the text] </output_format>