Update app.py

app.py

@@ -9,10 +9,7 @@ num_images = num_rows * num_cols
 image_size = 64
 plot_image_size = 64
 
-
-def load_model():
-    model = hf_hub.from_pretrained_keras("beresandras/denoising-diffusion-model")
-    return model
+model = hf_hub.from_pretrained_keras("beresandras/denoising-diffusion-model")
 
 def diffusion_schedule(diffusion_times, min_signal_rate, max_signal_rate):
     start_angle = tf.acos(max_signal_rate)
@@ -25,7 +22,7 @@ def diffusion_schedule(diffusion_times, min_signal_rate, max_signal_rate):
     
     return noise_rates, signal_rates
 
-def generate_images(model, num_images, diffusion_steps, stochasticity, min_signal_rate, max_signal_rate):
+def generate_images(diffusion_steps, stochasticity, min_signal_rate, max_signal_rate):
     step_size = 1.0 / diffusion_steps
     initial_noise = tf.random.normal(shape=(num_images, image_size, image_size, 3))
     
@@ -49,18 +46,12 @@ def generate_images(model, num_images, diffusion_steps, stochasticity, min_signa
         )
         
     generated_images = tf.clip_by_value(0.5 + 0.3 * pred_images, 0.0, 1.0)
-    generated_images = tf.image.resize(
-            generated_images, (plot_image_size, plot_image_size), method="nearest"
-    )
+    generated_images = tf.image.resize(generated_images, (plot_image_size, plot_image_size), method="nearest")
     return generated_images.numpy()
 
-
-model = load_model()
 gr.Interface(
     generate_images,
     inputs=[
-        model,
-        num_images,
         gr.inputs.Slider(1, 20, default=10, label="Diffusion steps"),
         gr.inputs.Slider(0.0, 1.0, step=0.05, default=0.0, label="Stochasticity"),
         gr.inputs.Slider(0.02, 0.10, step=0.01, default=0.02, label="Minimal signal rate"),