Update README.md

README.md

@@ -26,9 +26,8 @@ photo anime, masterpiece, high quality, absurdres
 Use negative prompts for best results, for example:
 ```
 simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy,
-bad proportions, extra digits, lowres, dated, username, artist name, error, out of frame, duplicate, watermark, signature, text,
-extra digit, fewer digits, worst quality, normal quality, jpeg artifacts, blurry, missing arms, bad hands, missing fingers, cropped,
-ugly, morbid, mutilated, extra fingers, mutated hands, deformed, gross proportions, second head
+bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality,
+jpeg artifacts, blurry
 ```
 
 **1girl**, **girl**, etc. give a bit different results, feel free to experiment and see which one you like more!
@@ -66,7 +65,8 @@ pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float
 pipe = pipe.to("cuda")
 
 prompt = "anime, masterpiece, high quality, 1girl, solo, long hair, looking at viewer, blush, smile, bangs, blue eyes, skirt, medium breasts, iridescent, gradient, colorful, besides a cottage, in the country"
-image = pipe(prompt).images[0]
+negative_prompt = 'simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry'
+image = pipe(prompt, negative_prompt=negative_prompt).images[0]
 
 image.save("./result.jpg")
 ```