Mixcat is just a product of my attempt to merge models, without any innovation or technology involved. It is all the result of predecessors. I think it's pretty good myself, so I'll share it.

Mixcat is a relatively clean basic model, and to obtain unique images, you need to collaborate with Lora and artist tags. Take a look at the example image.

Usage:

Similar to other Illustrious models, but CLIP Set Last Layer must be 2. If you are using ComfyUI, it will recognize itself and does not require CLIPSetLastLayer nodes.

You can choose between quality words and negative words at your own discretion.

Positive quality words: masterpiece, best quality, very awa, very aesthetic, absurdres, newest

Negative quality words: lowres, worst quality,bad quality,low quality, bad anatomy

Here are my parameters (you can definitely try other parameters, especially different samplers):

+ Sampler: Euler a or DPM++2m

+ Schedule: Beta

+ Steps: 20~25

+ CFG: 4~6

You can freely share this model, but you need to indicate the source and bear all the consequences caused by it yourself!