PixAI 會員
PixAI
PixAI
Generate
Sign in
主頁
生成
模型
Studio
NEW
比賽
用 Mio.2 創作
AI 工具
NEW
指南

用戶LoRA

XL
風格

[IL] Final Fantasy Dawn of Souls Style (Gen Kobayashi) / ファイナルファンタジーI・IIアドバンス作風 (小林 元)

#最終幻想

創作

  • AI 圖像生成器
  • AI 動畫生成器
  • AI 工具
  • 藝術主題產生器
  • 訓練 LoRA
  • Mio.2 智慧助手
  • Studio

探索

  • 熱門 Tags
  • 排名
  • 模型市場
  • 比賽
  • 新聞

關於

  • 指南
  • PixAI 部落格
  • Tsubaki.2
  • 認識 Mio,我們的吉祥物
  • 內容規則

定價與說明

  • 會員計劃
  • 購買點數
  • 聯絡

移動端 APP

  • App Store
  • Google Play
© 2026 PixAI
  • 服務條款
  • 隱私政策
  • 版權政策
  • 特定商業交易法
[IL] Final Fantasy Dawn of Souls Style (Gen Kobayashi) / ファイナルファンタジーI・IIアドバンス作風 (小林 元) - AI Model cover image
上傳時間
2025年11月14日 凌晨3:14
使用數
95
評論
暫無評論
觸發詞

F_F_D_O_S,, chibi only

許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

推薦 LoRA

tied up under clothes [写] DiT - AI Model cover image

用戶LoRA

tied up under clothes [写] DiT
8
Mana Umihara – Gotcha Force / マナ 海原 - ガチャフォース - AI Model cover image

用戶LoRA

Mana Umihara – Gotcha Force / マナ 海原 - ガチャフォース
0
001 — Sitrus Model Gallery - AI Model cover image

用戶LoRA

001 — Sitrus Model Gallery
1
Sena Akagi (赤城 瀬菜) - OreImo: My Little Sister Can't Be This Cute (俺の妹がこんなに可愛いわけがない) - AI Model cover image

用戶LoRA

Sena Akagi (赤城 瀬菜) - OreImo: My Little Sister Can't Be This Cute (俺の妹がこんなに可愛いわけがない)
7

描述

https://civitai.com/models/1606141/il-final-fantasy-dawn-of-souls-style-gen-kobayashi-iii-yuan

Attempts to recreate Gen Kobayashi’s artwork for the Final Fantasy 1+2 remake on the GBA, released in the west with the subtitle Dawn of Souls. I thought the style was neat (at least for FF1's simple, "vintage fantasy" designs. The parts of FF2's data that are more "overdesigned" don't look nearly as nice in it) and it seemed a decent candidate to try making.

Tags: F_F_D_O_S, Optional: chibi only (for humans. It's optional for monsters.) Aspect Ratio: SquareSoft (portrait tends to stretch characters and give them longer legs, thus ruining the chibi) The "chibi" tag is bugged in Illustrious and Pony to spawn copies of characters. Not sure how to fix it.

Trained off 36 transparent background images from Final Fantasy wiki’s FF1 and FF2 concept art pages, plus a pair of promo images of Chaos and Emperor cropped to face to avoid text and reused graphics. Flip augmentation used. Chose to do this primarily to test data needed for a style with limited scope (in this case, only character/monster images on a simple background). Works well, though wrangling with chibi's multiple views problem is a hassle (in fact, it's so much I'm not going to try the FFV chibi art I was considering doing as a followup unless someone can suggest how to avoid it).

Update: Version 1.2 changes all tags of "chibi" in training data to "chibi" only to try to clamp down on the multiple spawns thing and makes no other changes. It looks like it helps, but doesn't totally fix it.

評論