""" Ultra Supreme Optimizer - Main optimization engine for image analysis """ # IMPORTANT: spaces must be imported BEFORE torch or any CUDA-using library import spaces import gc import logging from datetime import datetime from typing import Tuple, Dict, Any, Optional import torch import numpy as np from PIL import Image from clip_interrogator import Config, Interrogator from analyzer import UltraSupremeAnalyzer logger = logging.getLogger(__name__) class UltraSupremeOptimizer: """Main optimizer class for ultra supreme image analysis""" def __init__(self): self.interrogator: Optional[Interrogator] = None self.analyzer = UltraSupremeAnalyzer() self.usage_count = 0 self.device = self._get_device() self.is_initialized = False @staticmethod def _get_device() -> str: """Determine the best available device for computation""" if torch.cuda.is_available(): return "cuda" elif torch.backends.mps.is_available(): return "mps" else: return "cpu" def initialize_model(self) -> bool: """Initialize the CLIP interrogator model""" if self.is_initialized: return True try: config = Config( clip_model_name="ViT-L-14/openai", download_cache=True, chunk_size=2048, quiet=True, device=self.device ) self.interrogator = Interrogator(config) self.is_initialized = True # Clean up memory after initialization if self.device == "cpu": gc.collect() else: torch.cuda.empty_cache() return True except Exception as e: logger.error(f"Initialization error: {e}") return False def optimize_image(self, image: Any) -> Optional[Image.Image]: """Optimize image for processing""" if image is None: return None try: # Convert to PIL Image if necessary if isinstance(image, np.ndarray): image = Image.fromarray(image) elif not isinstance(image, Image.Image): image = Image.open(image) # Convert to RGB if necessary if image.mode != 'RGB': image = image.convert('RGB') # Resize if too large max_size = 768 if self.device != "cpu" else 512 if image.size[0] > max_size or image.size[1] > max_size: image.thumbnail((max_size, max_size), Image.Resampling.LANCZOS) return image except Exception as e: logger.error(f"Image optimization error: {e}") return None @spaces.GPU def generate_ultra_supreme_prompt(self, image: Any) -> Tuple[str, str, int, Dict[str, int]]: """ Generate ultra supreme prompt from image Returns: Tuple of (prompt, analysis_info, score, breakdown) """ try: # Initialize model if needed if not self.is_initialized: if not self.initialize_model(): return "❌ Model initialization failed.", "Please refresh and try again.", 0, {} # Validate input if image is None: return "❌ Please upload an image.", "No image provided.", 0, {} self.usage_count += 1 # Optimize image image = self.optimize_image(image) if image is None: return "❌ Image processing failed.", "Invalid image format.", 0, {} start_time = datetime.now() # ULTRA SUPREME TRIPLE CLIP ANALYSIS logger.info("ULTRA SUPREME ANALYSIS - Maximum intelligence deployment") clip_fast = self.interrogator.interrogate_fast(image) clip_classic = self.interrogator.interrogate_classic(image) clip_best = self.interrogator.interrogate(image) logger.info(f"ULTRA CLIP Results:\nFast: {clip_fast}\nClassic: {clip_classic}\nBest: {clip_best}") # ULTRA SUPREME ANALYSIS ultra_analysis = self.analyzer.ultra_supreme_analysis(clip_fast, clip_classic, clip_best) # BUILD ULTRA SUPREME FLUX PROMPT optimized_prompt = self.analyzer.build_ultra_supreme_prompt( ultra_analysis, [clip_fast, clip_classic, clip_best] ) # CALCULATE ULTRA SUPREME SCORE score, breakdown = self.analyzer.calculate_ultra_supreme_score(optimized_prompt, ultra_analysis) end_time = datetime.now() duration = (end_time - start_time).total_seconds() # Memory cleanup if self.device == "cpu": gc.collect() else: torch.cuda.empty_cache() # Generate analysis report analysis_info = self._generate_analysis_report( ultra_analysis, clip_fast, clip_classic, clip_best, score, breakdown, duration ) return optimized_prompt, analysis_info, score, breakdown except Exception as e: logger.error(f"Ultra supreme generation error: {e}") return f"❌ Error: {str(e)}", "Please try with a different image.", 0, {} def _generate_analysis_report(self, ultra_analysis: Dict[str, Any], clip_fast: str, clip_classic: str, clip_best: str, score: int, breakdown: Dict[str, int], duration: float) -> str: """Generate detailed analysis report""" gpu_status = "⚡ ZeroGPU" if torch.cuda.is_available() else "💻 CPU" # Format detected elements - Fixed the .title() error by checking for None features = ", ".join(ultra_analysis["facial_ultra"]["facial_hair"]) if ultra_analysis["facial_ultra"]["facial_hair"] else "None detected" cultural = ", ".join(ultra_analysis["demographic"]["cultural_religious"]) if ultra_analysis["demographic"]["cultural_religious"] else "None detected" clothing = ", ".join(ultra_analysis["clothing_accessories"]["eyewear"] + ultra_analysis["clothing_accessories"]["headwear"]) if ultra_analysis["clothing_accessories"]["eyewear"] or ultra_analysis["clothing_accessories"]["headwear"] else "None detected" # Safe access to potentially None values age_category = ultra_analysis["demographic"].get("age_category", "Unspecified") if age_category and age_category != "Unspecified": age_category = age_category.replace("_", " ").title() setting_type = ultra_analysis["environmental"].get("setting_type", "Standard") if setting_type and setting_type != "Standard": setting_type = setting_type.title() primary_emotion = ultra_analysis["emotional_state"].get("primary_emotion", "Neutral") if primary_emotion and primary_emotion != "Neutral": primary_emotion = primary_emotion.title() analysis_info = f"""**🚀 ULTRA SUPREME ANALYSIS COMPLETE** **Processing:** {gpu_status} • {duration:.1f}s • Triple CLIP Ultra Intelligence **Ultra Score:** {score}/100 • Breakdown: Structure({breakdown.get('structure',0)}) Features({breakdown.get('features',0)}) Cultural({breakdown.get('cultural',0)}) Emotional({breakdown.get('emotional',0)}) Technical({breakdown.get('technical',0)}) **Generation:** #{self.usage_count} **🧠 ULTRA DEEP DETECTION:** - **Age Category:** {age_category} (Confidence: {ultra_analysis["demographic"].get("age_confidence", 0)}) - **Cultural Context:** {cultural} - **Facial Features:** {features} - **Accessories:** {clothing} - **Setting:** {setting_type} - **Emotion:** {primary_emotion} - **Total Features:** {ultra_analysis["intelligence_metrics"]["total_features_detected"]} **📊 CLIP ANALYSIS SOURCES:** - **Fast:** {clip_fast[:50]}... - **Classic:** {clip_classic[:50]}... - **Best:** {clip_best[:50]}... **⚡ ULTRA OPTIMIZATION:** Applied absolute maximum depth analysis with Pariente AI research rules""" return analysis_info