MeinaHentai Objective is to create NSFW illustrations without much need of Loras!
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
MeinaHentai is officially hosted for online generation in:
- SeaArt
- Mage.space ( with animate feature )
----------------------------------------------------------------------------------
-- Recommendations of use:
If you want the art to be more realistic, add: ' realistic ' or ' photo ' in the prompt.
---------------------------------------------
Recommended parameters:
Sampler: Euler a: 20~40 steps.
Sampler: DPM++ SDE Karras: 20~30 steps.
CFG Scale: 7.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 10 to 15 steps at 0.2 up to 0.4 denoising.
Clip Skip: 2.
Negatives: ' (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2), '
--------------------------------------------------------------------------------
Description
This is the very first version of MeinaHentai, using UNET block merge, i made so it will follow the prompt to the most of its capabilities.
Simple prompts with words such as sex, vaginal and sweat are enough to make hentai images in most cases. ( according prior testings )
As of right now, the hand generation is usually bad, upscalers with high denoising will break what the illustration were originally and may put a hand or arm in the place of the D*ck.
Recommendations:
- Sampling method: Euler a, 20 ~ 30 steps.
- Resolution: 512x768, 768x512.
- The VAE is baked-in.
- Upscaler: ESRGAN_4x at 10 steps and 0,3 Denoising in 2x.
- Negative prompt: ' (worst quality, low quality:1.4), monochrome, zombie, extra limbs, '
FAQ
Comments (7)
im wondering which vae work like the cover effection?
PickleTensor plz
The tools i use doesn't have the option for pickle :<
I can't use safetensor for same reason too. DiffusionBee work only with .ckpt models 😭
If this can be of any help:
- https://github.com/Akegarasu/sd-webui-model-converter
"convert to precisions: fp32, fp16, bf16 - pruning model: no-ema, ema-only - checkpoint ext convert: ckpt, safetensors"
- https://github.com/arenatemp/stable-diffusion-webui-model-toolkit
"Cleaning/pruning models - Converting to/from safetensors - Extracting/replacing model components"