ユーザーLoRA

DiT.3
キャラ

Senko-san_NAI-V5-Curated_ORIGINAL-ANIME_Tsubaki.3 (仙狐さん)

#ケモ耳#獣人#狐#妖狐#狐娘#世話やきキツネの仙狐さん#タフト#仙狐#もふもふケモミミ#ケモノ#椿
Senko-san_NAI-V5-Curated_ORIGINAL-ANIME_Tsubaki.3 (仙狐さん) - AI Modelのカバー画像
アップロード日時
2026/10/08 4:22
採用数
7
獲得
0
レビュー
大好評  (1)
トリガーワード

senko_san, senko_(sewayaki_kitsune_no_senko-san)

権限
  • 画像生成と共有を許可する
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

詳細説明

Anime-faithful character LoRA for Senko-san from The Helpful Fox Senko-san, for use with Tsubaki.3.

Built from an entirely new dataset of 99 native 1024 × 1024 NovelAI 5.0 Curated generations, this ORIGINAL-ANIME version captures the look and feeling of the original TV anime. Each training image was generated to resemble a frame from an episode, emphasizing softer linework, familiar colors, and faithful character design.

ORIGINAL-ANIME?

Where the HD version emphasizes ultra-crisp detail and high-fidelity rendering, ORIGINAL-ANIME prioritizes Senko’s on-screen likeness and the softer, screencap-like finish of the series. It is designed for txt2img and img2img character generation with strong identity consistency and flexible natural-language prompting.

This LoRA was built using the same prompt set and dataset structure as the previously released HD variant, with all images newly generated in NovelAI 5.0 Curated to match the original TV anime’s look. Its 50-image core character set establishes Senko’s identity across varied angles, expressions, poses, and framing, while its 49 activity scenes expand that foundation with the camera angles, shot types, and poses found across a wide range of activities. Why 99? PixAI's trainer was bugged and would not let me select the last 100th image. This should not significantly impact generation quality.

The Trigger Word:

senko_san

コメント

Senko-san_NAI-V5-Curated_ORIGINAL-ANIME_Tsubaki.3 (仙狐さん)で生成した作品