Create vision_model.py

vision_model.py

@@ -0,0 +1,13 @@
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from PIL import Image
+import torch
+
+model_id = "llava-hf/llava-1.5-7b-hf"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForVision2Seq.from_pretrained(model_id, torch_dtype=torch.float16).cuda()
+
+def describe_image(image_path, prompt="Describe this sculpt and any missing regions."):
+    image = Image.open(image_path).convert("RGB")
+    inputs = processor(prompt, image, return_tensors="pt").to("cuda", torch.float16)
+    output = model.generate(**inputs, max_new_tokens=150)
+    return processor.decode(output[0], skip_special_tokens=True)