Update README.md

README.md

@@ -20,23 +20,19 @@ tags:
 - **Prompt**: Use tag-based prompts to describe your subject.
   - Tag ordering matters. It is highly recommended to structure your prompt with the following templates:
     ```
-    1boy, male focus, character name, series name, anything else you'd like to describe, best aesthetic, amazing aesthetic, great aesthetic, normal aesthetic, best quality, amazing quality, great quality, normal quality, absurdres
+    1boy, male focus, character name, series name, anything else you'd like to describe, best quality, amazing quality, best aesthetic, absurdres
     ```
     ```
-    2boys, male focus, multiple boys, character name(s), series name, anything else you'd like to describe, best aesthetic, amazing aesthetic, great aesthetic, normal aesthetic, best quality, amazing quality, great quality, normal quality, absurdres
-    ```
-  - You don't need to use all the quality tags and aesthetic tags at once, but I found the results are better when all these tags are put into the prompt:
-    ```
-    , best aesthetic, amazing aesthetic, great aesthetic, normal aesthetic, best quality, amazing quality, great quality, normal quality
+    2boys, male focus, multiple boys, character name(s), series name, anything else you'd like to describe, best quality, amazing quality, best aesthetic, absurdres
     ```
 - **Negative prompt**: Choose from one of the following two presets.
-  1. Light (*recommended*):
+  1. Heavy (*recommended*):
     ```
-    lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic
+    lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts
     ```
-  2. Heavy:
+  2. Light:
     ```
-    lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts
+    lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic
     ```
 - **VAE**: Make sure you're using [SDXL VAE](https://huggingface.co/stabilityai/sdxl-vae/tree/main).
 - **Sampling method, sampling steps and CFG scale**: I find **(Euler a, 28, 8.5)** good. You are encouraged to experiment with other settings.
@@ -51,8 +47,8 @@ from diffusers import DiffusionPipeline
 pipe = DiffusionPipeline.from_pretrained("Koolchh/AnimeBoysXL-v3.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
 pipe.to("cuda")
 
-prompt = "1boy, male focus, shirt, solo, looking at viewer, smile, black hair, brown eyes, short hair, best aesthetic, amazing aesthetic, great aesthetic, normal aesthetic, best quality, amazing quality, great quality, normal quality, absurdres"
-negative_prompt = "lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic"
+prompt = "1boy, male focus, shirt, solo, looking at viewer, smile, black hair, brown eyes, short hair, best quality, amazing quality, best aesthetic, absurdres"
+negative_prompt = "lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts"
 
 image = pipe(
     prompt=prompt,