MeinaMix objective is to be able to do good art with little prompting.
I have a discord where you can share images, discuss prompt and ask for help. https://discord.gg/meinaverse
我有个可以让你分享图片和参与讨论与询问问题的discord群。
I also have a ko-fi and Patreon page where you can support me or buy me a coffee <3 , it will be very much appreciated:
https://ko-fi.com/meina and https://www.patreon.com/MeinaMix
MeinaMix is officially hosted for online generation in:
- SeaArt
- Mage.space ( with animate feature )
MeinaMix and the other of Meinas will ALWAYS be FREE.
Cover image lora made by: FallenIncursio | Civitai
Recommendations of use:
--------------------------------------------------------------------------------
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: DPM++ SDE Karras: 20 to 30 steps.
Sampler: DPM++ 2M Karras: 20 to 60 steps.
Sampler: Euler a: 40 to 60 steps.
CFG Scale: 4 to 9.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 10 steps at 0.3 up to 0.6 denoising.
Clip Skip: 2.
Negatives: ' (worst quality, low quality), (zombie, interlocked fingers) '
Negatives if you can't use Hires.fix:
'(worst quality:1.6, low quality:1.6), (zombie, sketch, interlocked fingers, comic)'
--------------------------------------------------------------------------------
In the merged models list: MeinaMix V1~11, MeinaPastel V3~6, MeinaHentai V2~5, Night Sky YOZORA Style Model, PastelMix, Facebomb, MeinaAlterV3 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.
Description
This version aims to retain the half realistic feel that MeinaMix have, while improving the capabilities of doing 2d and not realistic art.
Recommendations:
Euler a: 20 to 50 steps. OR DDIM: 20 to 50 steps.
CFG Scale between 5 to 9.
Resolutions of 512x768 or 768x512.
( it may be capable of doing 768x432 which is 16:9 but i've not tested).
Hires. fix: None or R-ESRGAN 4x, 10 Hires step, 0,3 to 0,6 Denoising.
Clip Skip 2.
The prompt can be simple or long, it will do fine without the meta tags. ( most of the samples do have meta tags because they're not mine. )
Negatives: ' (worst quality, low quality:1.4), [ng_deepnegative_v1_75t], (pale skin), '. ( pale skin is not needed but every now and then i would get very pale skin tone in the generations that had white hair )
As of right now, this was my favorite model to test, so i hope you guys enjoy it aswell!