retry8

app.py

@@ -93,8 +93,10 @@ class ImageInference:
         if use_cpu:
             print("Using CPU fallback mode (BLIP captioner + OCR)")
             try:
-                from transformers import pipeline
-                self.cpu_captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base", device=-1)
+                from transformers import AutoProcessor, AutoModelForVision2Seq
+                processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+                model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip-image-captioning-base")
+                self.cpu_captioner = {"processor": processor, "model": model}
             except Exception as exc:
                 raise RuntimeError(
                     "CPU fallback initialization failed. Ensure `torch` and `transformers` are installed. "
@@ -143,8 +145,11 @@ class ImageInference:
 
             # Run lightweight captioner
             try:
-                caption_result = self.cpu_captioner(image)
-                caption = caption_result[0].get("generated_text") or str(caption_result[0])
+                processor = self.cpu_captioner["processor"]
+                model = self.cpu_captioner["model"]
+                inputs = processor(images=image, return_tensors="pt")
+                outputs = model.generate(**inputs)
+                caption = processor.decode(outputs[0], skip_special_tokens=True)
             except Exception as exc:
                 caption = f"(caption failed: {exc})"
 
@@ -430,4 +435,4 @@ if __name__ == "__main__":
         theme=gr.themes.Soft(),
         css=CUSTOM_CSS,
         ssr_mode=False,
-    )
+    )