add: description.

app.py

@@ -13,6 +13,27 @@ from torchmetrics.image.inception import InceptionScore
 SEED = 0
 WEIGHT_DTYPE = torch.float16
 
+TITLE = "Evaluate Schedulers with StableDiffusionPipeline 🧨"
+DESCRIPTION = """
+This Space allows you to quantitatively compare different noise schedulers with a [`StableDiffusionPipeline`](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview).
+
+One of the applications of this Space could be to evaluate different schedulers for a certain Stable Diffusion checkpoint for fixed number of inference steps.
+
+Here's how it works:
+
+* The users provides:
+    * An input prompt.
+    * Number of images to generate with the prompt.
+    * A checkpoint path compatible with `StableDiffusionPipeline`. You can either select one from the drop-down list or provide a valid path ("valhalla/sd-pokemon-model" for example).
+    * Names of the schedulers to evaluate.
+* The evaluator first sets a seed and then generates the initial noise which is passed as the initial latent to start the image generation process. It is done to ensure fair comparison.
+* This initial latent is used every time the pipeline is run (with different schedulers).
+* To quantify the quality of the generated images we use:
+    * [Inception Score](https://en.wikipedia.org/wiki/Inception_score)
+    * [Clip Score](https://arxiv.org/abs/2104.08718)
+
+"""
+
 
 inception_score_fn = InceptionScore(normalize=True)
 torch.manual_seed(SEED)
@@ -186,6 +207,7 @@ demo = gr.Interface(
             ],
             value="CompVis/stable-diffusion-v1-4",
             multiselect=False,
+            interactive=True,
         ),
         gr.Dropdown(
             [
@@ -200,6 +222,8 @@ demo = gr.Interface(
         ),
     ],
     outputs=[gr.Markdown().style()],
+    title=TITLE,
+    description=DESCRIPTION,
     allow_flagging=False,
 )
 demo.launch()