Update app.py

app.py

@@ -113,7 +113,7 @@ with gr.Blocks() as demo:
                 Finally, an interesting aspect of the generations of the 3 models are the images themselves, which can be analyzed from different angles on a pixel-level. We explore the images in terms of their colorfulness using the [Colorfulness Profession Explorer](https://huggingface.co/spaces/tti-bias/identities-colorfulness-knn) and the [Colorfulness Identities Explorer](https://huggingface.co/spaces/tti-bias/professions-colorfulness-knn), which allow users to hone in on patterns in terms of colors and shades within the images generated. We also allow exploration of the images in terms of their visual features using the bag-of-visual-words approach (BoVW), which allows users to hone in on visual stereotypical content such as professions that have uniforms of a given color, of elements like glasses and hair styles -- this can be done via the [BoVW Nearest Neighbors Explorer](https://huggingface.co/spaces/tti-bias/identities-bovw-knn) and the [BoVW Professions Explorer](https://huggingface.co/spaces/tti-bias/professions-bovw-knn) -- we also present some of our salient findings in the accordion below.  
               """)   
     with gr.Accordion("Exploring the Pixel Space of Generated Images", open=False):
-         gr.HTML('''
+        gr.HTML('''
          <br>
          <p style="margin-bottom: 14px; font-size: 100%">  With thousands of generated images, we found it useful to provide ways to explore the data in a structured way that did not depend on any external dataset or model. We provide two such tools, one based on <b>colorfulness</b> and one based on a <b>bag-of-visual words</b> model computed using SIFT features.</p>
         ''')