Update README.md

README.md

@@ -16,7 +16,11 @@ Lots of images include visible nipples so, in case you don't want nsfw images, i
 Also, breasts tend to be large/huge so for anything smaller than that, use medium/small breasts on the prompts and large/huge breasts on the negative prompts, and skin tone tends to be 'tan' because of the same reason,
 so including tan/dark skin on the negative prompts and pale skin on the prompts will help to get whiter tones, though good anatomy gets affected.
 
-Token: 'sketchstyle' (depending on the model downloaded, you might have to use it just as it is, like in V3, not use it at all, like in V2 with high number of steps in the text encoder, and use it with a lot of strength, in the first models)
+Be sure to have this number over 75, and if possible not more than 95-100. Less than 75 will give bad results, with artifacts, and over that doesn't affect as much but works
+better between 80-90.
+![Screenshot_1.png](https://s3.amazonaws.com/moonup/production/uploads/1671505643175-633520c031a2be3938c9f8f5.png)
+
+Token: 'sketchstyle' (depending on the model downloaded, you might have to use it or not, if too much artifacts appear try to not include it, and if the style isn't apparent try to include it and/or strengthen it)
 
 The closer you are to 768x768, the better, but you can get good results in any resolution.
 
@@ -25,7 +29,10 @@ I recommend, if using V2, to use the 10k steps version as it has the least anato
 
 # Comparison between different versions and models
 
+As you can see, robutts tends to give less coherent results and might need more prompting/steps to get good results (tried on other things aswell with similar results)
 ![comparison.jpg](https://s3.amazonaws.com/moonup/production/uploads/1671502776323-633520c031a2be3938c9f8f5.jpeg)
+
+V2 with 10k steps or lower tends to give better anatomy results, and over that the style appears more apparent, so 10k is the 'sweet spot'.
 ![comparison2.jpg](https://s3.amazonaws.com/moonup/production/uploads/1671504780023-633520c031a2be3938c9f8f5.jpeg)
 
 # Examples for each version: