Update app.py

app.py

@@ -9,17 +9,19 @@ import spaces
 import torch
 from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
 
-#html_file_url = "https://prithivhamster.vercel.app/"
-#html_content = f'<iframe src="{html_file_url}" style="width:100%; height:400px; border:none"></iframe>'
-
-DESCRIPTIONx = """## STABLE HAMSTER 🐹"""
-
 css = '''
-.gradio-container{max-width: 575px !important}
+.gradio-container{max-width: 888px !important}
 h1{text-align:center}
 footer {
     visibility: hidden
 }
+.submit-btn {
+    background-color: #6263c7 !important;
+    color: white !important;
+}
+.submit-btn:hover {
+    background-color: #6063ff !important;
+}
 '''
 
 examples = [
@@ -30,14 +32,12 @@ examples = [
     "Cold coffee in a cup bokeh --ar 85:128 --v 6.0 --style raw5, 4K"
 ]
 
-#echo %VAR_NAME%
-MODEL_ID = os.getenv("MODEL_VAL_PATH") #Use SDXL Model as "MODEL_REPO" --------->>> ”VALUE”. 
+MODEL_ID = os.getenv("MODEL_VAL_PATH") 
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
 USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
 ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"
-BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1"))  # Allow generating multiple images at once
+BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1")) 
 
-#Load model outside of function
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 pipe = StableDiffusionXLPipeline.from_pretrained(
     MODEL_ID,
@@ -47,11 +47,9 @@ pipe = StableDiffusionXLPipeline.from_pretrained(
 ).to(device)
 pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
 
-# <compile speedup >
 if USE_TORCH_COMPILE:
     pipe.compile()
 
-# Offloading capacity (RAM)
 if ENABLE_CPU_OFFLOAD:
     pipe.enable_model_cpu_offload()
 
@@ -85,7 +83,6 @@ def generate(
     seed = int(randomize_seed_fn(seed, randomize_seed))
     generator = torch.Generator(device=device).manual_seed(seed)
 
-    #Options 
     options = {
         "prompt": [prompt] * num_images,
         "negative_prompt": [negative_prompt] * num_images if use_negative_prompt else None,
@@ -97,11 +94,9 @@ def generate(
         "output_type": "pil",
     }
 
-    #VRAM usage Lesser
     if use_resolution_binning:
         options["use_resolution_binning"] = True
 
-    #Images potential batches
     images = []
     for i in range(0, num_images, BATCH_SIZE):
         batch_options = options.copy()
@@ -112,21 +107,24 @@ def generate(
 
     image_paths = [save_image(img) for img in images]
     return image_paths, seed
-#Main gr.Block
+
 with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
-    gr.Markdown(DESCRIPTIONx)  
     with gr.Row():
-        prompt = gr.Text(
-            label="Prompt",
-            show_label=False,
-            max_lines=1,
-            placeholder="Enter your prompt",
-            container=False,
-        )
-        run_button = gr.Button("Run", scale=0)
-    result = gr.Gallery(label="Result", columns=1, preview=True, show_label=False)
+        with gr.Column(scale=1):
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            run_button = gr.Button(
+                "Generate as ( 1024 x 1024 )🤗", 
+                scale=0, 
+                elem_classes="submit-btn"
+            )
     
-    with gr.Accordion("Advanced options", open=False):
+    with gr.Accordion("Advanced options", open=True):
         num_images = gr.Slider(
             label="Number of Images",
             minimum=1,
@@ -183,6 +181,9 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                 value=23,
             )
 
+        with gr.Column(scale=2):
+            result = gr.Gallery(label="Result", columns=1, show_label=False)
+            
     gr.Examples(
         examples=examples,
         inputs=prompt,
@@ -216,6 +217,6 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
         outputs=[result, seed],
         api_name="run",
     )   
-    #gr.HTML(html_content)
+    
 if __name__ == "__main__":
     demo.queue(max_size=40).launch()