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 the 2nd version of Meina, the first version had too many flaws and i decided to hold on posting until i managed to fix the flaws, so here it is the Version 2, i'm working in testing the version 2.1 ( i posted a teaser of it in the kofi page ), the version 2.1 should be out within a week from now.
FAQ
Comments (3)
To add to the point about ENSD seemingly improving image quality: ENSD only affects ancestral samplers or DDIM (if you have enabled eta noise in DDIM); DPM++ SDE, as well as DPM++ SDE Karras are not ancestral samplers.
Thats something i didn't know, thank you for explaining what it actually do!! i had set the ENSD values because i was watching a video of how to setup the webui long ago, it makes sense now because back then DDIM was the main sampler i was using
@Meinaaa no problem. Eta noise is basically noise that a sampler adds to the image between processing steps, making the output less deterministic. By default, it's only applied by sampler with "a" at the end of their names (aka ancestral samplers, such as Euler a, or DPM 2S a Karras), but eta noise can also be applied to the DDIM sampler. DPM++ SDE Karras does not use eta noise regardless of settings, at least as far as the Automatic1111 web UI is concerned. I personally recommend using DDIM or Euler a for generating, DDIM for inpainting of less important details, and DPM++ SDE Karras for upscaling and face inpainting.