Update README.md

README.md

@@ -8,19 +8,19 @@ datasets: embed/EasyNegative
 
 ## Descriptions
 
-This model is suitable for reproducing images similar to anime screenshots, and it is recommended to use LoRA block weight expansion when using LoRA and character LoRA together. Setting the block weights of the character LoRA to presetting MIDD will reduce the distortion caused by the influence of the character LoRA on the style.
+This model is specifically designed to produce anime-style images and is recommended for use with both LoRA and character LoRA, with the LoRA block weight expansion setting. By adjusting the block weights of the character LoRA and using the MIDD preset, distortions caused by the character LoRA on the overall style can be minimized.
 
-It'll give you clean, good anatomy, and very anime-like pictures with beautiful backgrounds!
+Using this model will result in clean, anatomically-correct images that accurately capture the essence of anime-style art, complete with stunning backgrounds.
 
-There are two models provided, a LoRA model (which is only 36MB!) and a full base model (which is literally the LoRA model merged with Anything V4.5). The full model is provided for training your character model. I found it's good for training anime characters with this model.
+Two models are provided: an 18 MB LoRA model and a full base model that merges LoRA with Anything V4.5. The full model is recommended for training your character model, and is particularly effective for training anime characters using this model.
 
 ## Recommend settings:
 
- - VAE: Orangemix（the same with NAI）
+ - VAE: Orangemix (the same with NAI)
  - LoRA Strength: 1
  - Sampler: DPM++ 2M Karras
  - Sampling steps: 20
- - Negative embedding: EasyNegative、badhandv4
+ - Negative embedding: [EasyNegative](https://civitai.com/models/7808)、[badhandv4](https://civitai.com/models/16993/badhandv4-animeillustdiffusion)
 
 Highres fix is also recommended.