Update app.py

app.py

@@ -110,11 +110,11 @@ def generate_caption_and_image(image, f, p, d):
         # return generated_image, generated_image1
         messages = [{"role": "user", "content": [{"type": "image"},{"type": "text", "text": "If I had to write a haiku for this one, it would be: "}]}]
         input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
-        inputs = processor(image,input_text,add_special_tokens=False,return_tensors="pt").to(device)
+        inputs = processor(img,input_text,add_special_tokens=False,return_tensors="pt").to(device)
         
         output = model.generate(**inputs, max_new_tokens=30)
         caption =processor.decode(output[0])
-        image = pipe(prompt,height=1024,width=1024,guidance_scale=3.5,num_inference_steps=50,max_sequence_length=512,generator=torch.Generator("cpu").manual_seed(0)).images[0]
+        image = pipe(caption,height=1024,width=1024,guidance_scale=3.5,num_inference_steps=50,max_sequence_length=512,generator=torch.Generator("cpu").manual_seed(0)).images[0]
         return image
     return None
 # Gradio UI