# How to Configure Custom LLM Prompts for Image Descriptions in MarkItDown

> Master custom LLM prompts for image descriptions in MarkItDown. Learn to set the llm_prompt parameter to tailor AI-generated captions for your markdown documents.

- Repository: [Microsoft/markitdown](https://github.com/microsoft/markitdown)
- Tags: how-to-guide
- Published: 2026-04-11

---

**Set the `llm_prompt` parameter when initializing `MarkItDown` or calling `convert()` to override the default "Write a detailed caption for this image" instruction sent to multimodal LLMs.**

MarkItDown, Microsoft's open-source document conversion library, generates image captions using multimodal large language models when you provide an `llm_client` and `llm_model`. According to the microsoft/markitdown source code, you can fully customize the text prompt used for these descriptions at global, per-call, or per-converter scope without