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.
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.
This model does not include a safety checker (for NSFW content).

lightblackphoto-1.0:

Source(s): CivitAI

使用我自己拍摄的一些柔光暗调照片和一些网上类似的照片训练的真人照片模型。

注意事项：

1.只适用于1girl。

2.服饰在使用1girl和触发词时只有hanfu，Lolita，连衣裙和部分cosplay的tag会生效

3.背景在不写tag时候基本上都是黑暗森林，黑暗的房间。背景tag基本上都能成功触发

4.如果想对人物更多控制请不要输入1girl和触发词blackphoto。或者拉高cfg值

A real-life photo model trained using some soft-light and dark-tone photos I took myself and some similar photos from the Internet.

Precautions:

Only for 1girl.
When using 1girl and trigger words for clothing, only hanfu, Lolita, dresses and some cosplay tags will take effect
The background is basically a dark forest and a dark room when the tag is not written. Background tags can basically be successfully triggered
If you want more control over the characters, please do not enter 1girl and the trigger word blackphoto. Or raise the cfg value