Yotsugi Ononoki (Monogatari Series) — Illustrious SDXL Character LoRA

中文说明 | English (current)

An unofficial character LoRA for Yotsugi Ononoki (斧乃木余接) from Monogatari Series, trained on waiIllustriousSDXL v17. Formal E1–E7. Comparative evaluation recommends E6 at strength 0.8. Dataset: abbuibuibui/YotsugiOnonoki-Dataset.

Fan-made derivative, not official. Rights remain with the original owners.

Files

Epoch File Role
E1–E4 yotsugi_ononoki-000001 … 000004 Early / alternate.
E5 yotsugi_ononoki-000005.safetensors Matrix candidate.
E6 yotsugi_ononoki-000006.safetensors Recommended default.
E7 yotsugi_ononoki.safetensors Final epoch (unnumbered = E7).

No yotsugi_ononoki-000007.safetensors.

E6 SHA-256: 5F6DD21352BF88BD493D7D5C1342FDD628B0EBBE5507768F5549AF0A1FBD295D

Each file is 456490692 bytes.

Showcase

E6 @ 0.8, ComfyUI, Euler a / 28 / CFG 4.5 / CLIP skip 2 / 832×1216. No hires / ADetailer.

Face Main outfit full
Face Main
Alt outfit full Night street
Alt Night

No outfit token

Trigger Words and Settings

Captions used keep_tokens = 2; hair / eye color often omitted — add them. This pack has a single outfit token for main and alt eval.

Role Token Typical look
Identity yotsugi_ononoki twintails, white hair, green eyes
Outfit yotsugi_ononoki_orange_dress Orange frilly dress + signature orange hat (main=alt in this eval).

Example:

<lora:yotsugi_ononoki-000006:0.8>, masterpiece, best quality, very aesthetic, absurdres, anime screencap, 1girl, solo, yotsugi_ononoki, yotsugi_ononoki_orange_dress, twintails, white hair, green eyes, looking at viewer

Why E6

Round1 screened E1–E7 @ 0.8; Round3 matrix on E5–E7 × 10 scenes × 4 strengths.

Candidate Observed Decision
E5 Pale twintails / green eyes usable; orange hat often appears. Alternate.
E6 Portrait: pale teal/white twin tails, glassy green eyes, blank doll face, orange hat brim. Full body: tiered orange/red frilly dress, blue star bib, striped socks, yellow boots, googly-eye orange hat — classic tsukumogami silhouette. Recommended @ 0.8.
E7 Close to E6. Final alternate.

Chinese notes: evaluation/横向测评记录.md.

Public Horizontal Evaluation

Round 1: E1–E7 @ 0.8

Front portrait Main full
r1a r1b

r1c

Round 3: E5 / E6 / E7 × 0.4 / 0.6 / 0.8 / 1.0

Face Three-quarter Profile
01 02 03
Main full Alt full Sitting
04 05 06
Simple Night No outfit
07 08 09

10

Training

  • Base waiIllustriousSDXL v17; LoRA rank 64 / alpha 32; AdamW bf16; buckets cap 1536; 7 epochs
  • Dataset: 53 pairs (Orange_Dress only), repeats 3
  • Train / eval: NVIDIA DGX Spark + ComfyUI

Related

License

creativeml-openrail-m

Downloads last month
85
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train abbuibuibui/YotsugiOnonoki-Lora