Wa LoCon (NoobAI-XL)

Wa, a very awa LoCon extract of a NoobAI XL finetune.

Trained on NoobXL vpred, but compatible with other Illustrious/NoobAI-XL based mixes.

The finetuned model was trained using a select number of artists. The motivation behind this is to improve the aesthetics of the noob series of models, specifically on the anatomy and manga side of it.

I started training the noob model because I found that the style of some of my preferred artists could not be well replicated and the finetune kinda evolved from there. As of now, the dataset includes high-quality work from a total of 9 artists, and more might be added in the future.

Recommended settings

• Negative: lowres, worst quality, low quality, watermark, expressionless, no pupils

• Normal (~1MPx): Euler SMEA Dy CFG++ (1.5 cfg strength) & Beta/KL Optimal

• Hires (~3MPx): Kohaku_LoNyu_Yog (4.5 cfg strength, 0.4-0.7 denoise strength) & KL Optimal (warning: kohaku sampler is quite slow, but is more consistent for hires)

• Hires (~7MPx): Kohaku_LoNyu_Yog (4.5 cfg strength, 0.25-0.37 denoise strength) & KL Optimal

Examples (no artist tags)

Changelog:

• v12.2 (experimental) - NoobAI XL 1.0&v29b vpred mix

• v11.3 - NoobAI XL 0.75S vpred

• v7.1 - NoobAI XL 0.65S vpred