Update README.md

README.md

@@ -75,6 +75,7 @@ prompt: 1girl, solo, ball, swimsuit, bikini, mole, beachball, white bikini, brea
 ![image7](./000092_scribble_concat.webp)
 
 
+
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
@@ -194,3 +195,30 @@ images = pipe(
 
 images[0].save(f"your image save path, png format is usually better than jpg or webp in terms of image quality but got much bigger")
 ```
+
+
+## Evaluation Data
+The test data is randomly sample from popular wallpaper anime images(pixiv, nijijourney and so on), the purpose of the project is to letting everyone can draw an anime Illustration.
+We select 100 images and generate text with waifu-tagger[https://huggingface.co/spaces/SmilingWolf/wd-tagger] and generate 4 images per prompt, totally 400 images generated, the images
+should be 1024 * 1024 or same bucket resolution to acheive the best performance. We caculate the Laion Aesthetic Score to measure the beauty and the PerceptualSimilarity to measure the 
+control ability, we find the quality of images have a good consistency with the meric values. We compare our methods with other SOTA huggingface models and list the result below. We are 
+the models that have highest aesthectic score, and can generate visually appealing images if you prompt it properly.
+
+## Quantitative Result
+| metric | xinsir/anime-painter | lllyasviel/control_v11p_sd15_scribble |
+|-------|-------|-------|-------|
+| laion_aesthetic | **5.95** | 5.86 |
+| perceptual similarity | **0.5171** | 0.577 | 
+
+laion_aesthetic(the higher the better)  
+perceptual similarity(the lower the better)
+
+Note: The values are caculated when save in webp format, when save in png the aesthetic values will increase 0.1-0.3, but the relative relation remains unchanged.
+
+### Conclusion
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+In our evaluation, the model got better aesthetic score in anime images compared with lllyasviel/control_v11p_sd15_scribble, we want to compare with other sdxl-1.0-scribble model but find nothing, The model is better in control ability when test with perception similarity due to bigger base model and complex data augmentation.
+Besides, the model has lower rate to generate abnormal images which tend to include some abnormal human structure.
+