MoP Mixes are a series of checkpoints that merge the MoP (Mixture of Perverts) model with one other model that I find interesting. These are completely separate from the normal MoP releases because those are a much more complicated merge that requires a lot of testing. MoP Mixes are much simpler to produce with the goal of creating a MoP variation that hopefully some people may find useful or just fun.
To be clear, these MoP mixes should in no way be considered better than or a replacement for the checkpoint being merged with MoP. I strongly encourage you to download and test out the checkpoint for yourself and use it in the way that its author intended.
Each checkpoint will be set up in the manner that I think works best. So some of them will have the DMD2 LoRA fully integrated, some partially and some not at all. The recommended settings for each mix will most likely be different so check the About This Version section for all the details, as well as the recommended workflow.
Note: If you want to convert any of these DMD checkpoints to a non-DMD checkpoint then all you need to do is add the DMD LoRA and set the strength to a negative value. I would start with -0.85 and adjust from there. That will allow you to use a higher CFG and different samplers than LCM.
Fooocus Setup Instructions
1) Click the Advanced checkbox.
2) On the Settings tab, leave the Preset as 'initial' and the Performance as 'Speed'.
3) On the Models tab, set both the Base and Refiner models to MoP.
4) Change the Refiner Switch At setting to anywhere from 0.75 to 0.90. I like 0.85.
5) On the Advanced tab, change the Guidance Scale to 1.
6) Change the Positive ADM Guidance Scaler to 1.
7) Change the Sampler to 'lcm'. You can leave the Scheduler as Karras or Exponential.
8) Set the Forced Overwrite of Sampling Step to 7 to 11. I like 9.
Description
Note: Like v1, this BigASP 2.5 High v2 model is not a normal SDXL model and will probably only work in ComfyUI. It requires a special workflow that I'm not sure other image generation tools are capable of.
I've gone back and completely overhauled the high noise version of this model. It's one of my favorites and I wanted to start back on the raw Big ASP 2.5 base and then add five of my own trained style loras and the newest MoP v7.1 Flexible. You should still use the V1 Low model as the realistic refiner.
This model is now more capable at all types of images and not just realistic ones. It's very good at different 2D, 3D, comic and anime styles, especially when lightly refined using Illustrious.
Use the workflow embedded in any of the photographic showcase images. The cartoonish showcase images use a different workflow which is more effective at refining the high noise image. You'll want to use an Illustrious or Pony model as the refiner for that workflow for best results.
euler/beta or euler/ddim-uniform are the best scampler scheduler combos imo
~30 total steps - 22 high and 8 low is a good place to start
CFG 2.0-5.0 for High and 1.0-2.0 for Low