Edit model card

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.
  • Model versions listed with no-i2i in the file name do not contain a vae-encoder for use with the i2i feature.
  • 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).


Source(s): CivitAI

This is the blend I've been using for a while to generate some pics. It was born from my love of the skin textures and photorealistic look in Dreamlike Photoreal and my hate of how difficult it was to pose people in unorthodox ways. This merge tries to reach a good compromise, keeping skin textures and photo realistic capabilities while adding a ton of artistic and posing components, as well as some capability of understanding danbooru tags.

It's capable of some hardcore, but not the focus of the model at all, and therefore it's very hard to prompt.

The blend includes Dreamlike Photoreal, so here's the license. You have to follow it.




The links below lead to additional sample images. They are NSFW, 18+. Proceed with care.




Downloads last month
Hosted inference API

Unable to determine this model’s library. Check the docs .