clip-interrogator

import os from PIL import Image from clip_interrogator import Config, Interrogator # Create a dummy image for the example to be runnable dummy_image_path = "dummy_image_for_ci.jpg" try: Image.new('RGB', (224, 224), color = 'red').save(dummy_image_path) except ImportError: # Fallback if Pillow is not available for some reason (unlikely for this lib) with open(dummy_image_path, 'w') as f: f.write("dummy content") # Configure CLIP Interrogator ci_config = Config() # Set model names (these will be downloaded on first run and cached) ci_config.clip_model_name = "ViT-L-14/openai" ci_config.caption_model_name = "blip-large" # Other options: blip-base, blip2-2.7b, blip2-flan-t5-xl, git-large-coco # Apply low VRAM settings if available (recommended for GPUs with <12GB VRAM) # This method was introduced in v0.5.4 if hasattr(ci_config, 'apply_low_vram_defaults'): ci_config.apply_low_vram_defaults() # Initialize the Interrogator. This will download models if not already cached. print("Initializing CLIP Interrogator (models may download on first run)...") try: ci = Interrogator(ci_config) print("CLIP Interrogator initialized.") # Load an image image = Image.open(dummy_image_path).convert("RGB") # Perform interrogation prompt = ci.interrogate(image) print(f"Generated prompt: {prompt}") except Exception as e: print(f"Error during interrogation: {e}. Please ensure sufficient VRAM and disk space for models.") finally: # Clean up the dummy image if os.path.exists(dummy_image_path): os.remove(dummy_image_path)