Disabling HTML Encoding within Output of Custom Python Markdown Extension

I have been working on creating a python markdown extension that will insert an image gallery within my django project when a custom tag is used. The actual extension is working, but the HTML that the extension returns is all encoded. Here is the extension that I am using:

#!/usr/bin/env python
from django.template.loader import render_to_string
from main.models import *

import markdown

version = "0.1.0"

class GalleriaExtension(markdown.Extension):
    def __init__(self, configs):
        self.config = {
        }

        # Override defaults with user settings
        for key, value in configs:
            self.setConfig(key, value)

    def add_inline(self, md, name, klass, re):
        pattern = klass(re)
        pattern.md = md
        pattern.ext = self
        md.inlinePatterns.add(name, pattern, "<reference")

    def extendMarkdown(self, md, md_globals):
        self.add_inline(md, 'galleria', Galleria,
            r'\[\[(G|g)allery (?P<superpage_id>\w+)\]\]')

class Galleria(markdown.inlinepatterns.Pattern):
    def handleMatch(self, m):
        try:
            images = SuperPage.objects.get(id=m.group('superpage_id')).superpageimage_set.all()
        except:
            images = None
        if images:
            rendered = render_to_string('galleria.html', { 'images': images })
        else:
            rendered = '<b>There are no images for the given ID</b>'
        return rendered 

def makeExtension(configs=None) :
    return GalleriaExtension(configs=configs)

I ensured that the render_to_string was actually returning html that was not encoded. From the shell here is an example of the output:

Output from render_to_string:

>>> from django.template.loader import render_to_string
>>> images = SuperPage.objects.get(id=8).superpageimage_set.all()
>>> render_to_string('galleria.html', { 'images': images })
u'<div class=\'galleria_std\'>\n    <div class=\'gallery\' >\n      <div id=\'stage_gallery\' >\n'

Here is output from markdown extension that is encoded:

>>>markdown.markdown('test [[gallery 8]] test', ['galleria'])
u'<p>test &lt;div class=\'galleria_std\'&gt;\n    &lt;div class=\'gallery\' &gt;\n'

How can I make rendered return HTML mark up instead of encoded markup when using the markdown extension? Also, I would appreciate any pointers on coding this differently (syntax, layout, etc). I appreciate it.