Update app.py

app.py

@@ -38,11 +38,12 @@ def modify_caption(caption: str) -> str:
 
 def create_captions_rich(image: Image.Image) -> str:
     prompt = "caption en"
-    image_tensor = processor(image, return_tensors="pt").pixel_values.to("cpu")
+    # 이미지 데이터를 전처리하여 processor에 전달
+    image_tensor = processor(images=image, return_tensors="pt").pixel_values.to("cpu")
     model_inputs = processor(text=prompt, images=image_tensor, return_tensors="pt").to("cpu")
     input_len = model_inputs["input_ids"].shape[-1]
 
-    with torch.inference_mode():
+    with torch.no_grad():
         generation = model.generate(**model_inputs, max_new_tokens=256, do_sample=False)
         generation = generation[0][input_len:]
         decoded = processor.decode(generation, skip_special_tokens=True)
@@ -92,7 +93,7 @@ async def process_image(image_url, message):
 
 async def download_image(url):
     response = requests.get(url)
-    image = Image.open(io.BytesIO(response.content))
+    image = Image.open(io.BytesIO(response.content)).convert("RGB")  # 이미지 변환
     return image
 
 if __name__ == "__main__":