Update README.md

README.md

@@ -7,31 +7,39 @@ tags:
 - art
 - stable diffusion
 pipeline_tag: text-to-image
+library_name: diffusers
 ---
 
 MeinaMix Objective is to be able to do good art with little prompting.
 
 I created a discord server where you can post images that you generated, discuss prompt and/or ask for help.
-https://discord.gg/XC9nGZNDUd ( i'll be helping and answering questions there whenever i can! )
+https://discord.gg/XC9nGZNDUd 
 
 If you like one of my models and want to support their updates:
-I've made a ko-fi page where you can pay me a coffee <3 , it will be very much appreciated: https://ko-fi.com/meina
+I've made a ko-fi page: https://ko-fi.com/meina
+And a Patreon page:     https://www.patreon.com/MeinaMix
+
+where you can pay me a coffee <3 or support me and get acess to beta of my models! it will be very much appreciated!!
 
 MeinaMix and the other of Meinas will ALWAYS be FREE.
 
-(not updated to V8 yet) You may also try the latest version of my model using Sinkin.ai: https://sinkin.ai/m/vln8Nwr
+You may also try the latest version of my model using Sinkin.ai: https://sinkin.ai/m/vln8Nwr
 
 The images in the samples aren't cherry picked, if i had spent 2h to cherry pick each of the images it would hide how the model really performs and i don't think thats fair.
 
 Recommendations of use:
 --------------------------------------------------------------------------------
-Negative: ' (worst quality, low quality:1.4), monochrome, zombie, '
-
-The best samplers in most of the generations is DPM++ at 25 steps,  with a CFG scale of 5 up to 9. ( Clip skip 2. )
-
-As for the Hires.fix in most of the scenarios is R-ESRGAN 4x or +Anime6b, with 15 steps at 0.1 up to 0.3 denoising. 
---------------------------------------------------------------------------------
-
-In the merged models list: MeinaMix V1~6, MeinaPastel V3, MeinaHentai V2, Night Sky YOZORA Style Model, PastelMix and Facebomb, i do not have the exact recipe because i did multiple mixings using block weighted merges with multiple settings and kept the better version of each merge.
-
-I hope you have fun trying out my model, feel free to reach out to me in case you have any feedback to give!
+Enable Quantization in K samplers.
+
+Hires.fix is needed for prompts where the character is far away in order to make decent images, it drastically improve the quality of face and eyes!
+---------------------------------------------
+Recommended parameters:
+Sampler: Euler a: 40~60 steps.
+Sampler: DPM++ SDE Karras: 30~60 steps.
+CFG Scale: 7.
+Resolutions: 512x768, 512x1024 for Portrait!
+Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
+Hires.fix: R-ESRGAN 4x+Anime6b, with 10 steps at 0.1 up to 0.3 denoising.
+Clip Skip: 2.
+Negatives: ' (worst quality:2, low quality:2), (zombie, sketch, interlocked fingers, comic), '
+--------------------------------------------------------------------------------