Core ML Converted Model:
- This model was converted to Core ML for use on Apple Silicon devices. Instructions can be found here.
- Provide the model to an app such as Mochi Diffusion to generate images.
split_einsum
version is compatible with all compute unit options including Neural Engine.
Note: This model does not have the unet split into chunks.
Epic Diffusion:
Source(s): Hugging Face - CivitAI
Why Epic Diffusion Epîc Diffusion is a general purpose model based on Stable Diffusion 1.x intended to replace the official SD releases as your default model. It is focused on providing high quality output in a wide range of different styles, with support for NFSW content.
Epîc Diffusion 1.0 is a heavily calibrated merge of SD 1.4, SD 1.5, Analog Diffusion, Wavy Diffusion, Openjourney Diffusion, Samdoesarts Ultramerge, postapocalypse, Elldreth's Dream, Protogen V2.2, Inkpunk Diffusion, Arcane Diffusion & Van Gogh Diffusion blended and reblended multiple times until I got the quality & consistency I was looking for...