license: other
language:
- en
tags:
- anime
- art
- stable diffusion
pipeline_tag: text-to-image
This is a project of mine, i aim to make a model that doesn't take many words or complex prompts in order to draw a good image, making easy for everyone to use. I also aim to make the images usable as wallpaper, profile picture and use cases like those, so i'm often making changed in the model for it to look better.
I'll be updating the model every 1 to 2 weeks, also i'll be taking in consideration any feedback thats given to me.
If you like my model and wants to support me in making this project a sucess, you can buy me a coffee to keep me awake! https://ko-fi.com/meina
Recommendations of use:
- Negatives 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),'.
The best samplers in most of the generations is DPM++ SDE/DPM++ SDE Karass at 20 to 30 steps, Euler A at 50 steps, with a CFG scale of 5 up to 10.
As for the upscaler in most of the scenarios is R-ESRGAN 4x+ Anime6B, with 15 steps at 0.4 up to 0.6 denoising.
Clip skip 1 or 2.
I hope you have fun trying out my model, feel free to reach out to me in case you have any feedback to give!
In the merged models list: Meina Version 1, Kenshi, AbyssOrangeMix2, PastelMix and Grapefruit, 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.