Get all 100+ of my premium LoRA for free by joining my membership including Karina v12 on my kofi or buymeacoffee. If you want to make your own custom LoRA you can also contact me there.
Trigger word: aespakarina
Best checkpoint to generate the images for V8 and newer versions: ALEREAL
Recommended settings to use for v11 and newer version:
- Sampling method: DPM++ SDE Karras
- Sampling steps: 25 or more
- Use Hires fix: 8x_NMKD-Superscale_150000_G or 4x_foolhardy_Remacri.
Hires steps: 10
Denoising strength: 0,4
CFG scale: 7
- Negative prompts, always use this to get best outputs:
(paintings:2.0), (sketches:2.0), (worst quality:2.0), (low quality:2.0), (normal quality:2.0), (lowres:2.0), text, watermark, signature, artist name, rendering, 3D, painting, semi-realistic, anime, cartoon, unrealistic, fake
Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da
Use Clip Skip 2 and Hires Fix. This version is to fix overfitting outfit on v2 that almost always generated on some prompts. Is it better than v2? It should be, or you can buy the v6, v7 and v8, those for sure is better.
This version is based on Analog Diffusion and with dataset of Karina with her bangs hairstyle which I like it so much because it makes her looks sweet. It's difficult to search good images of her with that hairstyle, I had to edit many of them.
I think this looks good, don't compare this with v2 because it's totally different dataset and base model.