Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,56 @@
|
|
| 1 |
---
|
| 2 |
title: Image Evaluator
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 5.29.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Image Evaluator
|
| 3 |
+
emoji: 👁
|
| 4 |
+
colorFrom: purple
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 5.29.1
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Image Evaluator
|
| 13 |
+
|
| 14 |
+
Tool for evaluating and comparing images generated by different AI models.
|
| 15 |
+
|
| 16 |
+
## About
|
| 17 |
+
|
| 18 |
+
This Hugging Face Space provides a web interface for evaluating and comparing images generated by different AI models. It's particularly useful for developers, testers, and researchers working with image generation models, including those focused on artistic and anime styles.
|
| 19 |
+
|
| 20 |
+
## Features
|
| 21 |
+
|
| 22 |
+
- Upload and organize images by model
|
| 23 |
+
- Evaluate images using multiple metrics:
|
| 24 |
+
- Technical quality (sharpness, noise, artifacts)
|
| 25 |
+
- Aesthetic quality (color harmony, composition)
|
| 26 |
+
- Anime-specific metrics (line quality, style consistency)
|
| 27 |
+
- Compare different models with tables and visualizations
|
| 28 |
+
- Export results in various formats (CSV, JSON, HTML)
|
| 29 |
+
|
| 30 |
+
## How to Use
|
| 31 |
+
|
| 32 |
+
1. **Upload Images**: Go to the "Upload & Evaluate" tab, upload images for a specific model, and evaluate them
|
| 33 |
+
2. **Compare Models**: Go to the "Compare Models" tab to see which model performs best
|
| 34 |
+
3. **Export Results**: Save your evaluation results for further analysis
|
| 35 |
+
|
| 36 |
+
## Metrics
|
| 37 |
+
|
| 38 |
+
The tool evaluates images using three categories of metrics:
|
| 39 |
+
|
| 40 |
+
### Technical Metrics
|
| 41 |
+
- Sharpness: Measures image clarity and detail
|
| 42 |
+
- Noise: Measures absence of unwanted variations
|
| 43 |
+
- Artifacts: Measures absence of compression artifacts
|
| 44 |
+
- Saturation: Measures color intensity
|
| 45 |
+
- Contrast: Measures difference between light and dark areas
|
| 46 |
+
|
| 47 |
+
### Aesthetic Metrics
|
| 48 |
+
- Color Harmony: Measures how well colors work together
|
| 49 |
+
- Composition: Measures adherence to compositional principles
|
| 50 |
+
- Visual Interest: Measures how visually engaging the image is
|
| 51 |
+
|
| 52 |
+
### Anime-Specific Metrics
|
| 53 |
+
- Line Quality: Measures clarity and quality of line work
|
| 54 |
+
- Color Palette: Evaluates color choices for anime style
|
| 55 |
+
- Character Quality: Assesses character design and rendering
|
| 56 |
+
- Style Consistency: Measures adherence to anime style conventions
|