∞ 218 SDXL aka 'counterproductive illustration' omE
Merge of SDXL models I enjoyed with some extra flavors.
This took around 2 days of manual scoring and guidance through a Bayesian process, usually 500 samples per merge, which I did about 7 times total to arrive here. Also merged a LoRA trained on 18000 images at .4 weight into the final result, aimed at fixing sdxl models' lack of knowledge about the 4 letter word.
Usage
So this is a bit different compared to usual models. You can still prompt as normal, but there is a fun quirk thanks to Anime Illust Diffusion.
There is a wildcard text file in the repo that contains all the tags that call for their respective artstyles, try and play around with that.
After putting it in your wildcards folder, you can call it with ```__artistsAI__```
There is also a wildcard with artists that I personally liked in this model, ```__artists218__```, but this is a work in progress.
Artist xyzs thanks to b74 from the Touhou discord
Embeddings Downloads
VAE
∞ Credits
- Checkpoints
- Lynn for hf layout and future juice
- Ashtaka Aha Oof for taking my spam on discord EZ Clap
- Tools
Description
merge into turbo, for playing around mainly
if you can, use lcm sampler, euler a, 2m karras, or sde karras
start with 8 steps, and 2-4 cfg
pics are steps 8, lcm sampler