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.
• 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).
• This model can be used with ControlNet.

<br>

MyMerge-v1_cn:

MyMerge-v1 is a merge of 8 NSFW models from Civitai, all having open use licenses for non-commercial purposes. It was merged only from models that permit merging and other derivatives, and that allow for the uncredited free use of generated images. Hosting this model on for-profit image generation services/sites is, however, not permitted, due to restrictions inherited from one of the source models. This model does not contain ChillOut Mix, or other models which have a restrictive license.

The model is better suited to producing photo-realistic images than anime or other 2d illustration style images. Most of the source models were trained on 512x512 images. As you move towards 768x768, you will find that some generations may begin to distort.

Becauseof the NSFW nature of this model, sample images are not provided here. Refer to HassanBlend, Liberty, URPM, etc. at CivitAI to see where this model comes from and the type of image content that it is suited for.