Update app.py

app.py

@@ -51,13 +51,11 @@ def process_image_and_text(image_pil, num_beams, temperature, seed):
             device, dtype=torch.bfloat16
         )
         input_len = model_inputs["input_ids"].shape[-1]
-
-        # Set random seed for reproducibility, only if a seed is provided
-        if seed is not None:
-            torch.manual_seed(int(seed))
+        
+        torch.manual_seed(seed) # Set random seed for reproducibility
 
         with torch.inference_mode():
-            generation = model.generate(**model_inputs, max_new_tokens=200, do_sample=True, num_beams=num_beams, temperature=temperature)
+            generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=True, num_beams=num_beams, temperature=temperature)
             generation = generation[0][input_len:]
             decoded = processor.decode(generation, skip_special_tokens=True)
 
@@ -74,10 +72,10 @@ if __name__ == "__main__":
             gr.Image(type="pil", label="Upload an image"),
             gr.Slider(minimum=1, maximum=10, step=1, value=1, label="Number of Beams"),
             gr.Slider(minimum=0.1, maximum=2.0, step=0.1, value=1.0, label="Temperature"),
-            gr.Number(label="Random Seed", value=42, precision=0,  allow_none=True),
+            gr.Number(label="Random Seed", value=0, precision=0),
         ],
         outputs=gr.Textbox(label="Generated Text"),
-        title="PaliGemma2 Image to Text",
+        title="PaliGemma2 Image and Text to Text",
         description="Upload an image and enter a text prompt. The model will generate text based on both.",
     )
     iface.launch()