Update app.py

app.py

@@ -21,7 +21,7 @@ orig_clip_model, orig_clip_processor = clip.load("ViT-B/32", device=device, jit=
 # Load the Unsplash dataset
 dataset = load_dataset("jamescalam/unsplash-25k-photos", split="train")  # all 25K images are in train split
 
-height = 512   # height for resizing images
+height = 384   # height for resizing images
 
 def predict(image, labels):
     inputs = processor(text=[f"a photo of {c}" for c in labels], images=image, return_tensors="pt", padding=True)
@@ -107,7 +107,7 @@ def search(search_query):
 
 
 
-with gr.Blocks(css="#caption-text {font-size: 24px}") as demo:
+with gr.Blocks(css="#caption-text {font-size: 40px !important;}") as demo:
 
     with gr.Tab("Zero-Shot Classification"):
         labels = gr.State([])   # creates hidden component that can store a value and can be used as input/output; here, initial value is an empty list
@@ -147,7 +147,7 @@ with gr.Blocks(css="#caption-text {font-size: 24px}") as demo:
                 with gr.Row():
                     get_btn_cap = gr.Button("Get Random Image").style(full_width=False)
                     caption_btn = gr.Button("Create Caption").style(full_width=False)
-            caption = gr.Textbox(label='Caption', elem_id="caption-text").style(container=False)
+            caption = gr.Textbox(label='Caption', elem_id="caption-text")
         get_btn_cap.click(fn=rand_image, outputs=im_cap)
         #im_cap.change(generate_text, inputs=im_cap, outputs=caption)
         caption_btn.click(generate_text, inputs=[im_cap, model_name], outputs=caption)