Satoru Wada Art Style LoRA for Anima 3.8B

A style LoRA capturing the style @satoru_wada

Note: Trained on Delta Mix Anima (3.8B). I have not tested it on other Anima 3.8B models, so results on different checkpoints or base versions are not guaranteed.

Usage Settings

Base Model: Anima delta mix 3.8B

Trigger Word: @satoru_wada

Recommended LoRA Strength: 0.85 - 1.05 (1.0 is the sweet spot)

Sampler: euler_ancestral

Scheduler: simple

Dual-Pass CFG: Pass 1: 4.5 (11 steps) | Pass 2: 3.6 (15 steps, denoise 0.5)

Recommended Prompt Structure

@satoru_wada, safe, colossal dragon ...

@satoru_wada, safe, 1boy, knight, heavy armor, holding sword, facing colossal monster, giant serpent dragon ...

Training Details

Dataset: 50 hand-curated, high-resolution illustrations tagged with Danbooru tokens.

Architecture: Anima 3.8B LoRA (Rank 32, Alpha 128).

Epochs: 10 epochs (500 steps total), trained with AdamW.

Disclaimer: This model is intended for personal and non-commercial artistic exploration to study the visual style of @satoru_wada.