adding explanation texts

app.py

@@ -47,11 +47,12 @@ with gr.Blocks() as demo:
     gr.Markdown("""
                 ### Exploring Biases
             """)
-     
-
+    gr.Markdown("""
+                 Machine Learning models encode and amplify biases that are represented in the data that they are trained on -this can include, for instance, stereotypes around the appearances of members of different professions. In our study, we prompted the 3 text-to-image models with texts pertaining to 150 different professions and analyzed the presence of different identity groups in the images generated. We found evidence of many societal stereotypes in the images generated, such as the fact that people in positions of power (e.g. director, CEO) are often White- and male-appearing, while the images generated for other professions are more diverse. Read more about our findings in the accordion below or directly via the [Diffusion Cluster Explorer](https://huggingface.co/spaces/society-ethics/DiffusionClustering) tool.
+              """) 
     with gr.Accordion("Exploring Biases", open=False):
          gr.HTML('''
-         <p style="margin-bottom: 14px; font-size: 100%">  We also explore the correlations between the professions that use used in our prompts and the different identity clusters that we identified. <br> Using both the <a href='https://huggingface.co/spaces/society-ethics/DiffusionClustering' style='text-decoration: underline;' target='_blank'> Diffusion Cluster Explorer </a> and the <a href='https://huggingface.co/spaces/society-ethics/DiffusionFaceClustering' style='text-decoration: underline;' target='_blank'> Identity Representation Demo </a>, we can see which clusters are most correlated with each profession and what identities are in these clusters.</p>
+             <p style="margin-bottom: 14px; font-size: 100%">  We also explore the correlations between the professions that use used in our prompts and the different identity clusters that we identified. <br> Using both the <a href='https://huggingface.co/spaces/society-ethics/DiffusionClustering' style='text-decoration: underline;' target='_blank'> Diffusion Cluster Explorer </a> and the <a href='https://huggingface.co/spaces/society-ethics/DiffusionFaceClustering' style='text-decoration: underline;' target='_blank'> Identity Representation Demo </a>, we can see which clusters are most correlated with each profession and what identities are in these clusters.</p>
               ''')    
          with gr.Row():
             with gr.Column():
@@ -82,7 +83,9 @@ with gr.Blocks() as demo:
     gr.Markdown("""
                 ### Comparing Model Generations
             """) 
-    
+    gr.Markdown("""
+                Above and beyond quantitative analyses, one of the main goals of our project was to create accessible ways for the users to explore the generated images themselves, based on their own interests. For this purpose, we created two interactive tools: the [Diffusion Bias Explorer](https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer), which can be used to compare two models and the images they generate for a given profession or for a given model across two professions, and the [Average Diffusion Faces Tool](https://huggingface.co/spaces/society-ethics/Average_diffusion_faces), which shows an 'average' representation of faces across professions, based on the images generated by the 3 models.
+              """)     
     with gr.Accordion("Comparing Model Generations", open=False):
          gr.HTML('''
          <p style="margin-bottom: 14px; font-size: 100%">  One of the goals of our study was allowing users to compare model generations across professions in an open-ended way, uncovering patterns and trends on their own. This is why we created the <a href='https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer' style='text-decoration: underline;' target='_blank'> Diffusion Bias Explorer </a> and the <a href='https://huggingface.co/spaces/society-ethics/Average_diffusion_faces' style='text-decoration: underline;' target='_blank'> Average Diffusion Faces </a> tools. We show some of their functionalities below:    </p> ''')    
@@ -106,6 +109,9 @@ with gr.Blocks() as demo:
     gr.Markdown("""
                 ### Exploring the Pixel Space of Generated Images
             """) 
+    gr.Markdown("""
+                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('''
          <br>
@@ -120,7 +126,7 @@ with gr.Blocks() as demo:
                 ### All of the tools created as part of this project:
             """)
     gr.HTML('''
-     <p style="margin-bottom: 10px; font-size: 100%">
+     <p style="margin-bottom: 10px; font-size: 110%">
      <a href='https://huggingface.co/spaces/society-ethics/Average_diffusion_faces' style='text-decoration: underline;' target='_blank'> Average Diffusion Faces </a>  <br>
      <a href='https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer' style='text-decoration: underline;' target='_blank'> Diffusion Bias Explorer </a> <br> 
      <a href='https://huggingface.co/spaces/society-ethics/DiffusionClustering' style='text-decoration: underline;' target='_blank'> Diffusion Cluster Explorer </a> <br>