Image Evaluator
Tool for evaluating and comparing images generated by different AI models
How to Use Image Evaluator
Step 1: Upload Images
- Go to the "Upload & Evaluate" tab
- Upload images for a specific model
- Enter the model name
- Select which evaluators to use
- Click "Evaluate Images"
- Repeat for each model you want to compare
Step 2: Compare Models
- Go to the "Compare Models" tab
- Click "Compare Models" to see results
- The best model will be highlighted
- View charts for visual comparison
Step 3: View Metadata
- Go to the "Metadata Viewer" tab
- Upload an image to view its metadata
- Edit metadata if needed
Step 4: Export Results
- Go to the "Export Results" tab
- Select export format (CSV, JSON, HTML, or Markdown)
- Click "Export Results"
- Download the exported file
Available Metrics
Technical Metrics
- Sharpness: Measures image clarity and detail
- Noise: Measures absence of unwanted variations
- Artifacts: Measures absence of compression artifacts
- Saturation: Measures color intensity
- Contrast: Measures difference between light and dark areas
Aesthetic Metrics
- Color Harmony: Measures how well colors work together
- Composition: Measures adherence to compositional principles
- Visual Interest: Measures how visually engaging the image is
- Aesthetic Predictor: Score from Aesthetic Predictor V2.5 model
- Aesthetic Shadow: Score from Aesthetic Shadow model
Anime-Specific Metrics
- Line Quality: Measures clarity and quality of line work
- Color Palette: Evaluates color choices for anime style
- Character Quality: Assesses character design and rendering using Waifu Scorer
- Anime Aesthetic: Score from specialized anime aesthetic model
- Style Consistency: Measures adherence to anime style conventions