Update app.py

app.py

@@ -4,25 +4,31 @@ import gradio as gr
 
 # Load the Stable Diffusion model
 model_id = "runwayml/stable-diffusion-v1-5"  # Replace with your model if different
-pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)  # Use float32 for CPU
-pipe = pipe.to("cpu")  # Explicitly set to CPU
-
-# Enable CPU offloading to save memory (optional but recommended)
-pipe.enable_attention_slicing()  # Reduces memory usage by slicing attention computation
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
+pipe = pipe.to("cpu")
+pipe.enable_attention_slicing()  # Reduce memory usage on CPU
 
 # Define the generation function
 def generate_image(prompt, seed=None):
-    # If no seed is provided, generate a random one
+    # Handle the seed input
     if seed is None or seed == "":
+        # Generate a random seed if none provided
         seed = torch.randint(0, 1000000, (1,)).item()
-    
+    else:
+        # Convert the seed from string to integer
+        try:
+            seed = int(seed)
+        except ValueError:
+            # If conversion fails (e.g., user enters "abc"), use a random seed
+            seed = torch.randint(0, 1000000, (1,)).item()
+
     # Set up the generator with the seed for CPU
     generator = torch.Generator(device="cpu").manual_seed(seed)
     
-    # Generate the image with fewer steps for faster CPU execution
+    # Generate the image
     image = pipe(prompt, generator=generator, num_inference_steps=20).images[0]
     
-    return image, seed  # Return the image and the seed used
+    return image, str(seed)  # Return seed as string for display
 
 # Create Gradio interface
 interface = gr.Interface(