LoCon trained on Plebbles'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, artist name, signature, patreon

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

While I'm mostly satisfied with the model there are two primary problems I faced:

1. The eyes can be a little inconsistent, particularly with the shine. It's mostly learned how the eyes are drawn but still struggles even on facedetailer passes.

2. The torso/hips/groin are prone to odd folds and length issues. Can be partially mitigated with "fat rolls, ribs, big belly, hip bones" etc. in the negative prompt and more careful planning with the aspect ratio. This is highly dependent on the merge, however.

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

• Base Illustrious: ~1

• Base-like merges: ~1

• Poorly Compatible merges: <.6

• When mixing in a style .8 or less strength is good, but this is to your discretion

General Workflow for Sample Images (on ComfyUI):

• 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 .4 denoise

• A facedetailer is used after the upscale