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 is to a certain point a beta version. If theres anything wrong then i'll update it as soon as possible.
I will be publishing more samples later on, together with the version that doesn't have VAE baked in.
This version makes more illustration like images.
The hand generation is better than 3.0 in avarage.
It tends to make bodies overly skinny/fit or muscular. ( thats a pro and con ) -> samples included.
Better poses and more versatility.
As per request, now V4 will have a version without VAE ( will be uploaded within 24h).
-- Things still needed to work on
make the hand generation chance be higher chance of making good hands without the need of much finetuning in order to fix the fingers.
Some things like Eye glow i feel like it was better in 3.0, so i'll try to add it back in the 4.0+.
In the tests, the upscaler i often use ( R-ESRGAN 4x+ Anime6B ) broke the generation of hands more often than not, but lowering its value to lower than .50 seens to help in some cases.
It tends to make bodies skinny/fit or muscular. ( thats a pro and con ) -> Samples included.