---
license: creativeml-openrail-m
tags:
- coreml
- stable-diffusion
- text-to-image
---
# Core ML Converted Model:
- This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML).
- Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images.
- `split_einsum` version is compatible with all compute unit options including Neural Engine.
- `original` version is only compatible with `CPU & GPU` option.
- Custom resolution versions are tagged accordingly.
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model.
- This model was converted with a `vae-encoder` for use with `image2image`.
- This model is `fp16`.
- Descriptions are posted as-is from original model source.
- Not all features and/or results may be available in `CoreML` format.
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
- This model does not include a `safety checker` (for NSFW content).
# meinamix_meinaV10:
Source(s): [CivitAI](https://civitai.com/models/7240/meinamix)
MeinaMix objective is to be able to do good art with little prompting.
I created a discord server where you can post images that you generated, discuss prompt and/or ask for help. https://discord.gg/meinaverse
You may also try my model using Sinkin.ai: https://sinkin.ai/m/vln8Nwr
If you like one of my models and want to support their updates:
I 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 and the other of Meinas will ALWAYS be FREE.
The images in the samples aren't cherry picked, if i had spent 2h to cherry pick each of the images it would hide how the model really performs and i don't think thats fair.
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: Euler a: 40 to 60 steps.
Sampler: DPM++ SDE Karras: 30 to 60 steps.
Sampler: DPM++ 2M Karras: 20 to 60 steps.
CFG Scale: 4 to 11.
Resolutions: 512x768, 512x1024 for Portrait!
Resolutions: 768x512, 1024x512, 1536x512 for Landscape!
Hires.fix: R-ESRGAN 4x+Anime6b, with 15 steps at 0.4 denoising.
Clip Skip: 2.
Negatives: ' (worst quality, low quality:1.4), (zombie, sketch, interlocked fingers, comic), '
--------------------------------------------------------------------------------
In the merged models list: MeinaMix V1~6, MeinaPastel V3~5, MeinaHentai V2~3, Night Sky YOZORA Style Model, PastelMix and Facebomb, 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.