Application2

app.py

@@ -52,7 +52,7 @@ def inference(image, image_prompt):
     image = image.convert("RGB")  # Ensure image is RGB mode
 
     inputs = processor(text=prompt, images=image, return_tensors="pt")
-    generate_ids = base_model.generate(**inputs, max_new_tokens=15)
+    generate_ids = base_model.generate(**inputs, max_new_tokens=1024)
     decoded_response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
     return decoded_response