MeinaMix版本Meina V5 (ID: 12745)

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.

描述:

( This is the baked VAE version )
This is more very versatile version of Meina, it can do 2.5d, anime and near realistic!

This version is much much much more capable of making NSFW images, tho is wasn't what i was aiming at. ( last sample images )

The sample images had these settings:

R-ESRGAN 4x+Anime6B upscaled by 2x at 15 steps and 0,6 Denoising.

Base res: 512x768 / 768x512.

Clip skip 1.

Recommended Neg Prompt:

' (worst quality, low quality:1.4), (malformed hands:1.4),(poorly drawn hands:1.4),(mutated fingers:1.4),(extra limbs:1.35),(poorly drawn face:1.4), '

Now a bit of Lore:

It's a mix of Meina V3, with V4 and V4.1.
And it kept a little bit of each of them, i was focusing mostly in the hands but i liked the images that this version was capable of doing!

My focus in the V3 was to be 2.5d, V4 was to be anime like, now V5 is good at both!!

If you've read up to here: Thank you very much for giving a chance to my model! and also Thank you for everyone who have been following every update and posting pictures, i love seeing the amazing results you guys make which gives me more motivation to keep trying to improve!

Not even joking, this one took atleast 200 changes in the blocks and mixing %... >.>

训练词语: