| from transformers import pipeline | |
| def load_image_model(): | |
| """ | |
| Loads HuggingFaceTB/SmolVLM-500M-Instruct or another image-to-text model. | |
| """ | |
| return pipeline("image-to-text", model="HuggingFaceTB/SmolVLM-500M-Instruct") | |
| def analyze_image(image_file, image_model): | |
| """ | |
| Pass an image file to the image model pipeline and return the text/caption. | |
| """ | |
| result = image_model(image_file) | |
| if isinstance(result, list) and len(result) > 0: | |
| return result[0].get("generated_text", "No caption generated.") | |
| return "Unable to process image." | |