Hugging Face's logo

coreml-community
/
coreml-EvoArt-Mj4DreamMix

Text-to-Image
Core ML
stable-diffusion
Model card Files Community
coreml-EvoArt-Mj4DreamMix / README.md
mdmachine's picture
mdmachine
Update README.md
668fed0
preview code
|
raw
history blame contribute delete
1.78 kB
metadata
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. Conversion instructions can be found here.
  • Provide the model to an app such as Mochi Diffusion Github - Discord 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.
  • vae tagged files have a vae embedded into the model.
  • Descriptions are posted as-is from original model source. Not all features and/or results may be available in CoreML format.
  • This model was converted with vae-encoder for i2i.

Note: Some models do not have the unet split into chunks.

EvoArt-Mj4DreamMix:

Source(s): CivitAI

It is a Remix Model of some MJ4 style models like openjourney-v2 and other amazing models, specially with 3DKX model,and a little more 768+model in weight. so it can handle high-resolution output well.

I found it is a good effect when two similar style plus together. so you may look it as the mJ4-enhanced model.

To enhance the output,you can use "midjourney style" in the beginning of your prompt as trigger. Hypernetwork is not suggested，but <0.3 may lead to a different effect.