This is thanks to the project GuernikaKit from @GuiyeC.

The following are the new features since v5, which have not been merged into the original MochiDiffusion.

New Scheduler: LCM, DPM++ SDE Karras, Euler Ancenstral, etc.
New Model: LCM, SDXL Turbo, SDXL lightning etc.
New any model inpaiting support: special inpaiting model has better effect. (Any model needs to reduce its strength)
New painting interface: can control the size of the stroke.
New Control: ControlNet(SD1.5 and SDXL), T2I-Adapter(SD1.5 and SDXL) (Put the same folder as ControlNet, SDXL recommends using T2I-Adapter, which is smaller, faster and better picture quality)
New latent image decoder: used for the preview of the generation process without affecting the speed of generation.
Style prompt: A variety of stylized presets suitable for SDXL.
Variable Resolution: SD1.5 SDXL, Set the resolution completely freely, Free up your storage space.
Textual Inversion: You can add embeddings when using GuernikaModelConverter.
Weighted prompts: Increase the weight (prompt), reduce the weight [prompt].
No additional ControlledUnet.mlmodelc
More convenient model conversion tool.
Tip: Can disable CFG when converting the lcm, turbo, lightning model can reduce the generation time to half of the original, and the memory only needs 60% of the original.
Known problem: For the ordinary SDXL model, the DPM++ series sampler has image quality problems and needs to wait for the update. EulerA is used temporarily.
Note: It is no longer compatible with previously converted models.
new conversion tool: GuernikaModelConverter.dmg