modified: README.md

new file: configs/models.yaml
new file: tests/test_analyzer.py

README.md

@@ -1,13 +1,35 @@
----
-title: Arte Analyzer
-emoji: 🏆
-colorFrom: red
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.29.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Art Transformer 🎨
+
+Automatiza el análisis y transformación de álbumes de arte usando IA.
+
+## Características Principales
+- Análisis automático de obras de arte
+- Generación de marcos personalizados
+- Integración con Google Photos
+- Interfaz web con Gradio
+
+## Configuración en Hugging Face Spaces
+
+1. **Variables de Entorno:**
+   ```env
+   OPENAI_API_KEY=your_openai_key
+   GOOGLE_CLIENT_SECRET=your_google_client_secret
+   ```
+
+2. **Hardware:**
+   - GPU recomendada
+   - Memoria: Al menos 16GB
+
+3. **Ejecución:**
+   ```bash
+   pip install -r requirements.txt
+   python app.py
+   ```
+
+## Uso
+1. Sube tus imágenes
+2. Selecciona prioridad
+3. Espera los resultados
+4. Descarga las obras transformadas
+
+![Demo Interface](demo_screenshot.png)

configs/models.yaml

@@ -0,0 +1,14 @@
+default_models:
+  captioning: "Salesforce/blip2-opt-2.7b"
+  style_classifier: "dima806/art_painting_style_detection"
+  color_detector: "google/color-detector"
+  art_analysis: "ArtGAN/art-critique-generator"
+
+model_params:
+  captioning:
+    max_new_tokens: 150
+    temperature: 0.7
+    
+  art_analysis:
+    max_new_tokens: 250
+    temperature: 0.9

tests/test_analyzer.py

@@ -0,0 +1,38 @@
+import pytest
+from image_processor.analyzer import ImageAnalyzer
+from PIL import Image
+import numpy as np
+import logging
+
+@pytest.fixture
+def sample_image():
+    return Image.fromarray(np.random.randint(0, 255, (512, 512, 3), 'RGB')
+
+def test_initialization():
+    analyzer = ImageAnalyzer(device="cpu")
+    assert analyzer.models is not None
+    assert 'captioning' in analyzer.models
+
+def test_image_analysis(sample_image):
+    analyzer = ImageAnalyzer(device="cpu")
+    results = analyzer.analyze_image(sample_image)
+    
+    assert isinstance(results, dict)
+    assert 'title' in results
+    assert 'style' in results
+    assert len(results['colors']) == 5
+
+def test_error_handling():
+    analyzer = ImageAnalyzer(device="cpu")
+    invalid_input = "not_an_image"
+    
+    with pytest.raises(Exception):
+        analyzer.analyze_image(invalid_input)
+
+def test_color_detection(sample_image):
+    analyzer = ImageAnalyzer(device="cpu")
+    colors = analyzer._get_colors(sample_image)
+    
+    assert len(colors) == 5
+    assert all('hex' in c for c in colors)
+    assert all(0 <= c['score'] <= 1 for c in colors)