Warning: This model is created for non-commercial use only! By downloading and using this model, you agree to these terms. All images created by me are also copyrighted. For commercial use of my model, images, or generated images, or for selling my images or generated images, I will ban your public accounts (TG channel, Patreon, etc.). Please respect the intellectual property of the original creator/developer of this character! I created this LoRa to generate good art, sprites, and to help mod creators, not for business purposes.

P.S. For using my models or images outside of CivitAI, please provide a link to my model, my CivitAI profile, or tag me as the author. About images, I don't like porn and ugly things, I'm prefer sfw, questionable, aesthetic and ero-aesthetic images. If you like this model, BUZZ IT :)

Olesya from mod Dva for visual novel Everlasting Summer

V2

Lora trained on 166 images, works great, better works with prompt and very flexible.

I recommend using Hires.fix and Adetailer extensions for best results

Trigger Words:

1. olesya, brown eyes, short hair, black hair, red hair, two-tone hair, multicolored hair, streaked hair, 1girl, solo, (and sometimes medium breasts,)

2. olesya, black hair, short hair, multicolored hair, streaked hair, red hair, brown eyes, two-tone hair, bangs, parted lips,

Negative prompt: badge on the clothes, also some times patch,

Hires.fix: Hires steps 20 Denoising strength 0.4 Upscaler 4x-Ultrasharp or 4x NMKD Superscale, also ESRGAN_4x are not bad

Lora strength V2 0.7

Clip skip 2

V1

Lora trained on 55 images from the game in V1 so this lora are not very flexible, but with good prompt you can have great result!
I recommend using Hires.fix and Adetailer extensions for best results
I use checkpoint AutismMix_confetti
Trigger WordsV1: olesya, black hair, red hair, soft brown eyes, dark lips, short hair, solo, multicolored hair, streaked hair, two-tone hair, brown eyes

Negative prompt: patch, that is if you don't want sprite clothes
Hires.fix: Hires steps 20 Denoising strength 0.5 Upscaler 4x-Ultrasharp or 4x NMKD Superscale, also ESRGAN_4x are not bad

Lora strength 0.4-0.5 (i use 0.5 and that have best and stable results)

Clip skip 2