Create app.py

app.py

@@ -0,0 +1,43 @@
+import torch
+from diffusers import StableDiffusionPipeline
+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
+
+# Define the generation function
+def generate_image(prompt, seed=None):
+    # If no seed is provided, generate a random one
+    if seed is None or 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
+    image = pipe(prompt, generator=generator, num_inference_steps=20).images[0]
+    
+    return image, seed  # Return the image and the seed used
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=generate_image,
+    inputs=[
+        gr.Textbox(label="Prompt", placeholder="Enter your prompt here"),
+        gr.Textbox(label="Seed (optional)", placeholder="Leave blank for random")
+    ],
+    outputs=[
+        gr.Image(label="Generated Image"),
+        gr.Textbox(label="Seed Used")
+    ],
+    title="Stable Diffusion on CPU with Random Seed",
+    description="Generate images with Stable Diffusion on CPU. Leave seed blank for random output."
+)
+
+# Launch the interface
+interface.launch()