diff --git a/README.md b/README.md
index f0f2e83..6c72d0d 100644
--- a/README.md
+++ b/README.md
@@ -60,7 +60,7 @@ cat path-to-file.pdf | markitdown
 ```
 
 
-You can also configure markitdown to use Large Language Models to describe images. To do so you must provide mlm_client and mlm_model parameters to MarkItDown object, according to your specific client.
+You can also configure markitdown to use Large Language Models to describe images. To do so you must provide `mlm_client` and `mlm_model` parameters to MarkItDown object, according to your specific client.
 
 ```python
 from markitdown import MarkItDown
@@ -72,6 +72,13 @@ result = md.convert("example.jpg")
 print(result.text_content)
 ```
 
+The prompt of describing images can be customized by providing `mlm_prompt` parameter.
+
+```python
+# ...
+result = md.convert("example.jpg", mlm_prompt="Customized prompt")
+```
+
 ## Contributing
 
 This project welcomes contributions and suggestions.  Most contributions require you to agree to a
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 9517a32..39aa4c8 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -1160,7 +1160,7 @@ class MarkItDown:
                 self._append_ext(extensions, g)
 
             # Convert
-            result = self._convert(temp_path, extensions, url=response.url)
+            result = self._convert(temp_path, extensions, url=response.url, **kwargs)
         # Clean up
         finally:
             try: