Update README.md

README.md

@@ -39,11 +39,11 @@ tags:
 - **Negative prompt**: Choose from one of the following two presets.
   1. Heavy (*recommended*):
     ```
-    lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts
+    lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts, 1girl, breasts
     ```
   2. Light:
     ```
-    lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic
+    lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic, 1girl, breasts
     ```
 - **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, 5)** good. You are encouraged to experiment with other settings.
@@ -59,7 +59,7 @@ pipe = DiffusionPipeline.from_pretrained("Koolchh/AnimeBoysXL-v3.0", torch_dtype
 pipe.to("cuda")
 
 prompt = "1boy, male focus, shirt, solo, looking at viewer, smile, black hair, brown eyes, short hair, best quality, amazing quality, best aesthetic, amazing 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"
+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, 1girl, breasts"
 
 image = pipe(
     prompt=prompt,