Original character LoRA for Lin Wanxing / 林晚星, trained on the Anima base model (anima-base-v1.0).

Trigger word: lin_wanxing — use the token exactly as written, underscore included.

lwx_default is a secondary token for the character's default outfit (present in 4 of 40 captions).

Trained at 1024×1024 with bucketing, 40 images × 10 repeats, network dim 16 / alpha 8, AdamW8bit at 1e-4 with a cosine schedule and 200 warmup steps. This release is the epoch-8 checkpoint (3200 steps), not epoch-10.

ComfyUI-converted (*_comfy.safetensors).