Update README.md

README.md

@@ -4,10 +4,15 @@ license: apache-2.0
 <h1 align="center"><strong style="font-size: 48px;">AniMixV9XL AnimeTV Mix</strong></h1>
 AnimeTV/Screencap Fine-tuned Model's Based on AutismMixXL & PonyV6.
 
+The model gives a stable, predictable result. Therefore, I recommend using seed with increasing the number of steeps when satisfied with the “draft” with a small number of steps. 
+But predictability and forecasting have the other side of the coin: the model is not flexible and is quite limited in variations.
+
+Keep in mind that the results between different versions of the model differ, although not significantly.
+
 ### Optimal Generation Options
 - __Sampler__: Euler A. (LCM+ Can Work too, just lower the steps and CFG)
 
-- __Steps__: <span style="color:red">20-28</span>
+- __Steps__: <span style="color:red">20-28</span> (min 12)
 
 - __CFG__: <span style="color:red">4.5-7</span> (5.5 CFG = Best of both world in my Opinion)
 
@@ -48,5 +53,5 @@ Don't use negative prompts or Embedding that will deterior the Style.
 ### Source:
 [civitai](https://civitai.com/models/454878/animixv9xl-animetv-mixscreencap)
 
-## Support
+## Support me
 [buymeacoffee](https://buymeacoffee.com/raingart). Thank you for support!