Noxnox (Noxintwice) - LyCORIS LoCon - Illustrious

LoCon trained on Noxnox (@Noxintwice)'s artstyle for Illustrious models

General usage Notes:

For more specific issues check the "about this version" section of the specific model.

Thus far my most successful permanent positive/negative combo is:

masterpiece, best quality, good quality

lowres, worst quality, low quality, oldest, jpeg artifacts, blurred, artist name, signature

This likely changes depending on settings and merges, but I've not needed to modify them.

This model has two distinct styles:

General style appears to be more like his more recent works
"Flat color, no lineart" appears to be his older style that uses significantly less linework

Strength depends on merge lora compatibility and what you're trying to do, generally:

I haven't tested base Illustrious
On very compatible merges alone I recommend 1
On poorly compatible merges I don't recommend going over .7
When mixing in a style .8 or less strength is good (depending on the style used) but this is to your discretion

Images marked with "Noobai v.75" are actually V11

Sampler from images is done with Restarts with segments of [3,2,0.06,0.30], which are values from the paper on Restarts
- Note: Using restarts tends to smooth out the image more but makes it more coherent, your mileage may vary and it's up to you if you want to use them
No special scheduler is used
Conditioning is split (A1111 BREAK) into 3 parts, generally BG and camera/Subject Face and attributes/Subject body and clothing
Initial resolution is selected from the SDXL whitepaper appendix I: https://arxiv.org/pdf/2307.01952
Image is upscaled by 1.5x using Lanczos resampling
Second sample pass is the same, but at around 15 steps at .3 denoise
A facedetailer is used after the upscale