Update README.md

README.md

@@ -17,12 +17,23 @@ license: creativeml-openrail-m
 <div align="center">
 <a href="https://huggingface.co/Ocean3/SuperMix/tree/main/1)%20Versions">Models</a> | <a href="https://huggingface.co/Ocean3/SuperMix/tree/main/3)%20Alternate%20Versions">Alt Versions</a> | <a href="https://civitai.com/models/110537" target="_blank">CivitAI Page</a></div>
 
-m
+This model keeps surprising me and reigns currently as one of my favorites generally speaking as well as among my unreleased/released mixes. I made this mix one day after experimenting with some other merges using MBW. I essentially started with an uncommon base and used some common to uncommon weight presets testing by eye merging in aspects of models as I went.
+
+The final result really brings together some of the styling I enjoy in a neutral fashion. Some great detail, great texture and lighting/reflections, semi-soft/muted tones, and an overall mostly-stable creative flexibility with prompts and configurations across the board. Hopefully you enjoy this one as much as I have ~ feel free to let me know!
+
+💡 Preview images and examples can be found on the <a href="https://civitai.com/models/110537" target="_blank">CivitAI page</a>.
 
 ---
 # General Use
 <img src="https://cdn.discordapp.com/attachments/1054203646717472833/1130921231063973928/NE_TitleBanner7.png" title=general-use>
 
+I've found this model is decently **flexible** - use what you find best for this model(s). The preview image and gallery sections can give you a good base as a starting point. Start with a good prompt and go from there. Be keen of any conflicting styles and how tokens may 'lean' the model toward one style or another. Some prompts may be a bit messy, but overall should be able to be toned down or reworked.
+
+For a soft/neutral anime style, keep prompts from being too heavy on realistic tokens. You can enhance an anime style (or others) with related terms. This model currently loses a bit of clarity/detail with eyes at a mid-far to far character distance depending. This can be remedied at times by either changing your prompt to exclude certain tokens such as **full body** and/or upscaling the image once again using the img2img upscaler. Hires fix upscale initially is already assumed to be used.
+
+I've found a lot of samplers work great being fairly similar across the board with this version. Have fun and try some common and uncommon configurations.
+
+
 <i>**~20** steps, **7** cfg scale, **~0.4** denoising, clip skip **1 or 2**, is a good starting point</i>
 
 ---