Update README.md

README.md

@@ -22,7 +22,7 @@ Begin the prompt with **((oil painting))** for the oil paint effect. For digital
 
 Paint Journey V2's paintings tend to be closer to human-drawn than Open Journey V2.
 Unlike some models such as DreamShaper, this model is capable of generating stunning portraits at 768x1144 resolution without duplicated faces.
-Compared to models like Dreamlike Diffusion 1.0, this model tends to generate 768x768 or higher resolution outputs with reduced noise.
+Compared to models like Dreamlike Diffusion 1.0, this model tends to generate 768x768 or higher resolution images with reduced noise.
 
 
 ## Training
@@ -65,6 +65,7 @@ image = pipe(prompt).images[0]
 image.save("./result.png")
 ```
 
-## Safety Checker
+## Safety Checker V2
 
-The official [stable diffusion safety checker](https://huggingface.co/CompVis/stable-diffusion-safety-checker) uses up 1.22GB VRAM. Recommend using [Google Safesearch Mini](https://huggingface.co/FredZhang7/google-safesearch-mini) (99MB) to save 1.12GB VRAM.
+The official [stable diffusion safety checker](https://huggingface.co/CompVis/stable-diffusion-safety-checker) uses up 1.22GB VRAM.
+I recommend using [Google Safesearch Mini V2](https://huggingface.co/FredZhang7/google-safesearch-mini-v2) (220MB) to save 1.0GB VRAM.