Update app.py

app.py

@@ -70,7 +70,7 @@ Below is the simple caption of an image with text. Please deduce the detailed de
 
     response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
     enhanced_caption = response.split("</think>", -1)[-1].strip(" ").strip("\n")
-
+    model.to("cpu")
     torch.cuda.empty_cache()
     
     return combined_caption, enhanced_caption
@@ -98,7 +98,7 @@ def generate_image(enhanced_caption, seed, num_inference_steps, guidance_scale):
         generator=generator,
         system_prompt="You are an assistant designed to generate superior images with the superior degree of image-text alignment based on textual prompts or user prompts.",
     ).images[0]
-
+    pipe.to("cpu")
     torch.cuda.empty_cache()
     
     return image