Update app.py

app.py

@@ -216,8 +216,19 @@ def infer(prompt, negative_prompt, image, model_type="Standard"):
 with gr.Blocks(theme='gradio/soft') as demo:
     gr.Markdown("## Stable Diffusion with Hand Control")
     gr.Markdown("This model is a ControlNet model using MediaPipe hand landmarks for control.")
+    gr.Markdown("""
+<center><h2><b>LINKS 🔗</b></h2>
+<h4 style="text-align: center;"><a href="https://huggingface.co/Vincent-luo/controlnet-hands">Standard Model Link</a></h4>
+<h4 style="text-align: center;"> <a href="https://huggingface.co/MakiPan/controlnet-encoded-hands-130k/">Model using Hand Encoding</a></h4>
+<br>
+<h4 style="text-align: center;"> <a href="https://huggingface.co/datasets/MakiPan/hagrid250k-blip2">Dataset Used To Train the Standard Model</a></h4>
+<h4 style="text-align: center;"> <a href="https://huggingface.co/datasets/MakiPan/hagrid-hand-enc-250k">Dataset Used To Train the Hand Encoding Model</a></h4>
+<br>  
+<h4 style="text-align: center;"> <a href="https://github.com/Maki-DS/Jax-Controlnet-hand-training/blob/main/normal-preprocessing.py">Standard Data Preprocessing Script</a></h4>
+<h4 style="text-align: center;"> <a href="https://github.com/Maki-DS/Jax-Controlnet-hand-training/blob/main/Hand-encoded-preprocessing.py">Hand Encoding Data Preprocessing Script</a></h4></center>
+""")
     model_type = gr.Radio(["Standard", "Hand Encoding"], value="Standard", label="Model preprocessing", info="We developed two models, one with standard MediaPipe landmarks, and one with different (but similar) coloring on palm landmarks to distinguish left and right")
-
+    
     with gr.Row():
         with gr.Column():
             prompt_input = gr.Textbox(label="Prompt")
@@ -265,8 +276,8 @@ with gr.Blocks(theme='gradio/soft') as demo:
         cache_examples=True,
     )
             
-    inputs = [prompt_input, negative_prompt, input_image, model_type]
-    submit_btn.click(fn=infer, inputs=inputs, outputs=[output_image])
+        inputs = [prompt_input, negative_prompt, input_image, model_type]
+        submit_btn.click(fn=infer, inputs=inputs, outputs=[output_image])
     
     gr.Markdown("""
 <center><h1>Summary</h1></center>
@@ -277,7 +288,7 @@ We opted to use the [HAnd Gesture Recognition Image Dataset](https://github.com/
 <br>
 To preprocess the data there were three options we considered:
 <br>
-    -The first was to use Mediapipes built-in draw landmarks function. This was an obvious first choice however we noticed with low training steps that the model couldn't easily distinguish handedness and would often generate the wrong hand for the conditioning image.<center>
+    > * The first was to use Mediapipes built-in draw landmarks function. This was an obvious first choice however we noticed with low training steps that the model couldn't easily distinguish handedness and would often generate the wrong hand for the conditioning image.<center>
 <br>
 <table><tr>
 <td> 
@@ -297,7 +308,7 @@ To preprocess the data there were three options we considered:
 </tr></table>
 </center>
 <br>
-    -To counter this issue we changed the palm landmark colors with the intention to keep the color similar in order to learn that they provide similar information, but different to make the model know which hands were left or right.<center>
+    > * To counter this issue we changed the palm landmark colors with the intention to keep the color similar in order to learn that they provide similar information, but different to make the model know which hands were left or right.<center>
 <br>
 <table><tr>
 <td> 
@@ -317,20 +328,9 @@ To preprocess the data there were three options we considered:
 </tr></table>
 </center>
 <br>
-    -The last option was to use [MediaPipe Holistic](https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html) to provide pose face and hand landmarks to the ControlNet. This method was promising in theory, however, the HaGRID dataset was not suitable for this method as the Holistic model performs poorly with partial body and obscurely cropped images.
+    > * The last option was to use [MediaPipe Holistic](https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html) to provide pose face and hand landmarks to the ControlNet. This method was promising in theory, however, the HaGRID dataset was not suitable for this method as the Holistic model performs poorly with partial body and obscurely cropped images.
 <br>
 We anecdotally determined that when trained at lower steps the encoded hand model performed better than the standard MediaPipe model due to implied handedness. We theorize that with a larger dataset of more full-body hand and pose classifications, Holistic landmarks will provide the best images in the future however for the moment the hand encoded model performs best. """)
 
-    gr.Markdown("""
-<center><h2><b>LINKS 🔗</b></h2>
-<h3 style="text-align: center;"><a href="https://huggingface.co/Vincent-luo/controlnet-hands">Standard Model Link</a></h3>
-<h3 style="text-align: center;"> <a href="https://huggingface.co/MakiPan/controlnet-encoded-hands-130k/">Model using Hand Encoding</a></h3>
-<br>
-<h3 style="text-align: center;"> <a href="https://huggingface.co/datasets/MakiPan/hagrid250k-blip2">Dataset Used To Train the Standard Model</a></h3>
-<h3 style="text-align: center;"> <a href="https://huggingface.co/datasets/MakiPan/hagrid-hand-enc-250k">Dataset Used To Train the Hand Encoding Model</a></h3>
-<br>  
-<h3 style="text-align: center;"> <a href="https://github.com/Maki-DS/Jax-Controlnet-hand-training/blob/main/normal-preprocessing.py">Standard Data Preprocessing Script</a></h3>
-<h3 style="text-align: center;"> <a href="https://github.com/Maki-DS/Jax-Controlnet-hand-training/blob/main/Hand-encoded-preprocessing.py">Hand Encoding Data Preprocessing Script</a></h3></center>
-""")
 
 demo.launch()