Improved description

app.py

@@ -209,12 +209,12 @@ intro = """
 Gradio demo for the blind face image restoration version of [Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration](https://arxiv.org/abs/2410.00418). 
 You may use this demo to enhance the quality of any image which contains faces.
 
-PMRF is a novel photo-realistic image restoration algorithm. It (provably) approximates the optimal estimator that minimizes the Mean Squared Error (MSE) under a perfect perceptual quality constraint. Please refer to our project's page for more details: https://pmrf-ml.github.io/.
+PMRF is a novel photo-realistic image restoration algorithm. It (provably) approximates the optimal estimator that minimizes the Mean Squared Error (MSE) under a perfect perceptual quality constraint. Our model in this demo is specifically tailored for blind face image restoration. Please refer to our project's page for more details: https://pmrf-ml.github.io/.
 
 *Notes* : 
 
-1. Our model is designed to restore aligned face images, where there is *only one* face in the image, and the face is centered and aligned. Here, however, we incorporate mechanisms that allow restoring the quality of *any* image that contains *any* number of faces. Thus, the resulting quality of such general images is not guaranteed.
-2. If the faces in your image are not aligned, make sure that the checkbox "The input is an aligned face image" in *not* marked.
+1. Our original model is designed to restore low-quality face images, where the image is square, there is *only one* face in the image, and the face is centered and aligned. In this demo, however, we incorporate mechanisms that allow restoring the quality of *any* image that contains *any* number of faces. Thus, the resulting quality of such general images is not guaranteed.
+2. If your image is not an aligned and square face image, make sure that the checkbox "The input is an aligned and square face image" in *not* marked.
 3. Too large images may result in out-of-memory error.
 """
 
@@ -244,19 +244,12 @@ This project is released under the <a rel="license" href="https://github.com/oha
 If you have any questions, please feel free to contact me at <b>guyoep@gmail.com</b>.
 """
 
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 512px;
-}
-"""
-
 demo = gr.Interface(
     inference,
     [
         gr.Image(label="Input", type="filepath", show_label=True),
         gr.Checkbox(label="Randomize seed", value=True),
-        gr.Checkbox(label="The input is an aligned face image", value=False),
+        gr.Checkbox(label="The input is an aligned and square face image", value=False),
         gr.Slider(
             label="Scale factor (applicable to non-aligned face images)",
             minimum=1,
@@ -266,7 +259,7 @@ demo = gr.Interface(
             scale=1,
         ),
         gr.Slider(
-            label="Number of Inference Steps",
+            label="Number of inference steps (a larger number should lead to better image quality)",
             minimum=1,
             maximum=200,
             step=1,