Sign In

Eguchi Kokoro 江口こころ — Tonari no Seki no Yatsu ga Souiu Me de Mitekuru となりの席のヤツがそういう目で見てくる [Anima+Illustrious]

5

Updated: Oct 30, 2026

charactermanga

Not recently loaded

Download

1 variant available

fp16 SafeTensor

eguchi_illustrious_v1.safetensors

Half precision, best balance • 217.9 MB

Verified:

Type
LoRA
Stats

99

0

Generation License Fee

1 / 1 image

Reviews
Published

Aug 13, 2026

Base Model
Hash
AutoV2C12F0D3642
Trigger Words
eguchitonari
01_cover_classroom.png

Early access on Patreon: new LoRAs for free, 7 days early / 新作LoRAを無料で7日早くダウンロード

💬 Discord — join here / 参加はこちら · 🔓 Patreon — new LoRAs 7 days early / 新作LoRAを7日早く · ☕ Ko-fi — support the factory / 応援する · 💼 Request Commission / コミッション依頼

Eguchi Kokoro 江口こころ — Tonari no Seki no Yatsu ga Souiu Me de Mitekuru となりの席のヤツがそういう目で見てくる

The girl one desk over — glasses on, purple stare, ink optional.


Character LoRA for Eguchi Kokoro, the female lead of mmk's manga — The Mortifying Ordeal of Being Seen in VIZ's English edition. The trigger eguchitonari carries her whole look — long wavy dark brown hair, round glasses, droopy purple eyes, her moles and pale skin. None of it was left in the captions — the trigger is the entire appearance block.

She is a two-mode LoRA: weight monochrome, greyscale up for the manga's own ink, or keep those words in the negative for colour.

🧩 Version

  • 🔵 v1.0 Anima — for Anima / Qwen-Image DiT checkpoints. ✅ Works in the Civitai on-site generator. Weight 1.0 (usable range 0.85 – 1.0).

  • 🟢 v1.0 Illustrious — for SDXL / Illustrious / Pony / NoobAI checkpoints. Weight 0.85 – 1.0.

  • 🟠 Remapped Anima 2.9B — this version is the same LoRA remapped onto the 40-layer Anima-2.9B layout (weight 0.5–0.7, no patch node needed). It is a remap, not a retrain, so there may be issues with the 2.9B version — if there is enough interest I may retrain it natively for 2.9B.

#1 in AnimeJapan's 2026 want-animated ranking — no adaptation announced yet.

📋 Prompt

Colour — the negative is part of the prompt on this one:

eguchitonari, white shirt, collared shirt, black skirt

Negative — keep all four:

monochrome, greyscale, comic, speech bubble

Manga mode — same words, moved to the positive:

eguchitonari, (monochrome:1.6), (greyscale:1.6), (black and white:1.4), comic, collared shirt
negative: color, colored, spot color, sepia

Festival — her biggest outfit cluster:

eguchitonari, yukata, floral print, hair flower, obi

💡 Tips

  • That negative is not optional in colour mode. A bare prompt slides back into ink, borders and bubbles. Add english text if scanlation lettering survives.

  • For real manga mode, push the words hard. Her baked colour identity resists going grey — plain monochrome leaks a tinted hybrid, so use the weighted stack above with color in the negative.

  • The glasses are baked into the trigger — they come with her. glasses in the negative takes them off.

  • Outfits stay steerable. The bear hoodie (hoodie, animal hood, hood up), school uniform, pajamas and swimsuit are all trained. ponytail is a tag too — she defaults to hair down.

  • Colour mode learned from two-person art — 17 of the 20 colour images have the boy from the next desk in them. Keep solo in unless you want him.


More of my LoRAs: Techannel on Civitai — likes & Buzz keep the factory running ❤️