Instructions to use abbuibuibui/YotsugiOnonoki-Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use abbuibuibui/YotsugiOnonoki-Lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("waiIllustriousSDXL", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("abbuibuibui/YotsugiOnonoki-Lora") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
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.
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
Round 3: E5 / E6 / E7 × 0.4 / 0.6 / 0.8 / 1.0
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
- HF model: https://huggingface.co/abbuibuibui/YotsugiOnonoki-Lora
- HF dataset: https://huggingface.co/datasets/abbuibuibui/YotsugiOnonoki-Dataset
- ModelScope model: https://www.modelscope.cn/models/abbuibuibui/YotsugiOnonoki-Lora
- ModelScope dataset: https://www.modelscope.cn/datasets/abbuibuibui/YotsugiOnonoki-Dataset
License
creativeml-openrail-m
- Downloads last month
- 85

















