Soraoraora Style | Anima LoRA

The original artist stopped to draw and I wanted to replicate the style on Anima and wasn't really satisfied with what we currently had on Civitai. Still, credit to https://civarchive.com/user/gothwomenenjoyer who did a great job with this style.

Soraoraora style LoRA trained for Anima on 162 non-synthetic images from the original artist and 13 synthetic images, recreating the distinctive rendering, facial features, body proportions, linework, and color palette of Soraoraora.

Recommended Settings

Base model: Anima Base / Anima-derived checkpoints
LoRA weight: 0.9–1.35
CFG: 3–6
Steps: 25–35

Can be use without trigger word.

Sampler: er_sde works very well, other Euler-class samplers work well.

If you get good results, feel free to post them on the model page.
Feedback is welcome, especially if you notice prompts where the style does not apply well.