|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
tags: |
|
|
- coreml |
|
|
- stable-diffusion |
|
|
- text-to-image |
|
|
--- |
|
|
# Core ML Converted Model (split_einsum only!): |
|
|
|
|
|
- This model was converted to Core ML for use on Apple Silicon devices. Instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-files-to-Core-ML).<br> |
|
|
- Provide the model to an app such as [Mochi Diffusion](https://github.com/godly-devotion/MochiDiffusion) to generate images.<br> |
|
|
- `split_einsum` version is compatible with all compute unit options including Neural Engine.<br> |
|
|
|
|
|
# Note: This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). |
|
|
|
|
|
# Protogen_x2.2 by [darkstorm2150](https://instagram.com/officialvictorespinoza): |
|
|
Source(s): [Hugging Face](https://huggingface.co/darkstorm2150/Protogen_v2.2_Official_Release) |
|
|
|
|
|
Protogen was warm-started with Stable Diffusion v1-5 and fine-tuned on a large amount of data from large datasets new and trending on civitai.com. |
|
|
|
|
|
You can enforce camera capture by using the prompt with "modelshoot style". |
|
|
|
|
|
It should also be very "dreambooth-able", being able to generate high fidelity faces with a little amount of steps [(see dreambooth)](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth). |
