I decided to do a big mashup of 8 of my recent SDXL models just to see how it would come out, and I got this. I wouldn't call the style super distinctive, but it's a nice anime model that renders at high detail and can do hands and bodies without any serious flaws. It's also quite good at landscapes and architecture, and follows short prompts well. I imagine it will be a good base for further training and mixing.
See this article for details about my generation settings.
Description
This is a precursor to Mega Mix that stands on its own, although it's too similar to be a separate model upload.
FAQ
Comments (3)
I downloaded this a few days ago and have generated several images, they all seem to be washed out and often have blow out. Does this require a separate vae to be loaded, or is one baked in? If so which one?
I'm running this with the standard SDXL VAE.
I am having the same issue with all of your checkpoints :/ its like they have had a sepia filter.
Edit. I figured it out, setting the VAE to TASED in decode fixed the issue.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.