Skip to content

💃 Free CC0 mannequin pose reference library for AI image tools (Nano Banana, ChatGPT, ComfyUI, Midjourney) — 250+ poses × 5 angles in line art, names in ja/zh/en/ko

docs(web): hero title 姿势参考, README taglines and sizes cover the maps, new screenshot

wqugurufa488253739e
diff --git a/AGENTS.md b/AGENTS.md
index 65e87e17..b2c5bc44 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -7,7 +7,8 @@ includes this file.
A self-made pose reference library: faceless mannequin line art, each pose drawn from five angles (front, diag,
side, above, below), for people who drive AI image tools with pose references. Four series: `std` full body
(P###, 73 sets), `upper` upper body (U###, 80), `sexy` full body (S###, 80) and `duo` two figures (D###, 55); the last
-two are rated suggestive. Plus photo renders for 23 std sets, a four-language catalog (ja / zh / en / ko) and a static gallery in `web/`.
+two are rated suggestive. Plus photo renders for 23 std sets, clay / depth / normal maps for most passed views (made
+from the line art and aligned with it), a four-language catalog (ja / zh / en / ko) and a static gallery in `web/`.
## 2. Hard rules
- **No outside images.** Never download, cache, mirror, re-encode or trace images from ai-pose-gallery
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5c99b192..0e3aae7c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,13 @@ the catalog schema.
## [Unreleased]
+### Changed
+- Chinese hero title 姿势参考 · 五机位: the site has five formats now, so the title names none of them; 线稿 stays in
+ the line below and in the page title.
+- README: the tagline in all four languages mentions the clay, depth and normal maps; the repository size note covers
+ the maps and the costume library (it said 63 MB); a new screenshot of the hero with the mixed-format marquee.
+ AGENTS.md describes the maps in §1.
+
## [0.4.1] - 2026-10-31
### Changed
diff --git a/README.md b/README.md
index 2c9e498a..703c356c 100644
--- a/README.md
+++ b/README.md
@@ -4,8 +4,8 @@
# Shisei 姿勢
-**A free (CC0) mannequin pose reference library: 280 poses in four series × 5 camera angles, drawn as clean line art
-for Nano Banana, ChatGPT, ComfyUI, Midjourney and other AI image tools.**
+**A free (CC0) mannequin pose reference library: 280 poses in four series × 5 camera angles, drawn as clean line art,
+most views also as clay, depth and normal maps, for Nano Banana, ChatGPT, ComfyUI, Midjourney and other AI image tools.**
English · [简体中文](docs/readme/README.zh-CN.md) · [日本語](docs/readme/README.ja.md) · [한국어](docs/readme/README.ko.md)
@@ -28,7 +28,7 @@ English · [简体中文](docs/readme/README.zh-CN.md) · [日本語](docs/readm
> nudity detail). They stay out of previews and search pages, and the gallery shows them blurred until you tap one
> or flip the switch.
-[![Shisei gallery: hero with a marquee of mannequin poses on pastel category tiles](docs/screenshot.png)](https://shisei.indaloop.app/en/)
+[![Shisei gallery: hero with a marquee mixing line-art poses on pastel tiles with clay, depth and normal maps](docs/screenshot.png)](https://shisei.indaloop.app/en/)
Shisei is a self-made pose reference library. Every pose is a faceless mannequin drawn from five angles — front,
three-quarter, side, above and below — so you can feed the same pose to an image model from whichever camera you
@@ -73,8 +73,9 @@ the figure consistent across shots. Face, clothing and background come from your
| `w900` | `images/*/w900/` | 900 × 1200 | ~29 KB |
| full | [original zip](#downloads) | 1344 × 1792 (photos 1120 × 2240, redrawn sets 900 × 1200) | ~100 KB |
-The repository holds the three web tiers (about 63 MB). The full-size originals and ready-made zips are on the
-[Releases](https://github.com/wquguru/shisei/releases) page.
+The repository holds the three web tiers: about 145 MB for the poses (line art, photos and the clay, depth and
+normal maps), plus about 150 MB for the costume library. The full-size originals and ready-made zips are on the
+[Releases](https://github.com/wquguru/shisei/releases) page; most people only need a zip.
### Downloads
diff --git a/docs/DESIGN.md b/docs/DESIGN.md
index d3db4c69..0436c996 100644
--- a/docs/DESIGN.md
+++ b/docs/DESIGN.md
@@ -15,7 +15,7 @@
## 页面结构(桌面)
1. 导航:logo 胶囊、姿势 / 分类 ▾ / 机位 ▾ / 实拍 / 使用方法 / 更新日志,右侧语言菜单(地球图标 + 当前语言名 ▾)、深色模式、GitHub。不做搜索(2026-10-29 去掉)。
-2. 首屏:大标题(中文「姿势线稿参考」:「白模」只指白模格式,素体线稿叫素体)、一句说明(提到三种新格式)、两行反向滚动的姿势方块(尊重 `prefers-reduced-motion`)、各系列套数胶囊、「浏览 N 套姿势」「下载图包 [大小]」、适用工具。
+2. 首屏:大标题(中文「姿势参考 · 五机位」,2026-10-31:站上有五种格式,标题不点名其中一种;「线稿」留在说明句和网页标题里。「白模」只指白模格式,素体线稿叫素体)、一句说明(提到三种新格式)、两行反向滚动的姿势方块(尊重 `prefers-reduced-motion`)、各系列套数胶囊、「浏览 N 套姿势」「下载图包 [大小]」、适用工具。
N 是全部已发布的套数(有通过质检的机位),不随性感内容开关变化;没有写死的数字。
3. 全部姿势:吸顶筛选条(分类胶囊带色点和数量、机位、线稿/实拍、按姿势/逐张、计数),下面是网格。
4. 页脚:只写一句「全部素材由 Shisei 自制。」加链接,不提其他项目。
diff --git a/docs/readme/README.ja.md b/docs/readme/README.ja.md
index 121c1478..3aad5c63 100644
--- a/docs/readme/README.ja.md
+++ b/docs/readme/README.ja.md
@@ -4,7 +4,7 @@
# Shisei 姿勢
-**無料(CC0)の素体ポーズ集。4 シリーズ 280 ポーズ × 5 アングルの線画を、Nano Banana・ChatGPT・ComfyUI・Midjourney など画像生成 AI のポーズ指定にそのまま使えます。**
+**無料(CC0)の素体ポーズ集。4 シリーズ 280 ポーズ × 5 アングルの線画(ほとんどのアングルはクレイ・深度・法線マップ付き)を、Nano Banana・ChatGPT・ComfyUI・Midjourney など画像生成 AI のポーズ指定にそのまま使えます。**
[English](../../README.md) · [简体中文](README.zh-CN.md) · 日本語 · [한국어](README.ko.md)
@@ -25,7 +25,7 @@
> **ご注意:**全身・セクシーとふたりのシリーズは、やや性的な成人向けポーズ参考です(素体、露出の描写なし)。プレビューや検索用ページには出さず、ギャラリーでは初期状態でぼかしてあり、1 枚ずつタップするかスイッチを入れると見られます。
-[![Shisei ギャラリー:カテゴリ色のタイルに素体ポーズが並ぶトップ画面](../screenshot.png)](https://shisei.indaloop.app/ja/)
+[![Shisei ギャラリー:カテゴリ色のタイルの線画に、クレイ・深度・法線マップが混ざって流れるトップ画面](../screenshot.png)](https://shisei.indaloop.app/ja/)
Shisei は自作のポーズ参照ライブラリです。すべてのポーズは顔なしの素体で、正面・斜め・横・上から・下からの五つのアングルで描いています。必要なカメラ位置の一枚をそのまま画像モデルに渡せます。ポーズ名とカテゴリは日本語・中国語・英語・韓国語の四か国語です。
@@ -60,7 +60,7 @@ Shisei は自作のポーズ参照ライブラリです。すべてのポーズ
| `w900` | `images/*/w900/` | 900 × 1200 | 約 29 KB |
| 原寸 | [原寸の zip](#ダウンロード) | 1344 × 1792(実写 1120 × 2240、描き直したセット 900 × 1200) | 約 100 KB |
-リポジトリには Web 用の 3 サイズ(約 63 MB)だけを置いているので、クローンは軽く済みます。原寸とまとめた zip は [Releases](https://github.com/wquguru/shisei/releases) ページにあります。
+リポジトリには Web 用の 3 サイズを置いています(ポーズは線画・実写・クレイ・深度・法線で約 145 MB、ほかに衣装ライブラリが約 150 MB)。ほとんどの人は zip だけで十分です。原寸とまとめた zip は [Releases](https://github.com/wquguru/shisei/releases) ページにあります。
### ダウンロード
diff --git a/docs/readme/README.ko.md b/docs/readme/README.ko.md
index 8d116d6b..d562f4ba 100644
--- a/docs/readme/README.ko.md
+++ b/docs/readme/README.ko.md
@@ -4,7 +4,7 @@
# Shisei 姿勢
-**무료(CC0) 마네킹 포즈 자료. 4개 시리즈 280가지 포즈 × 5개 앵글의 선화를 Nano Banana, ChatGPT, ComfyUI, Midjourney 등 AI 그림 도구의 포즈 참고로 바로 쓸 수 있습니다.**
+**무료(CC0) 마네킹 포즈 자료. 4개 시리즈 280가지 포즈 × 5개 앵글의 선화(대부분의 앵글에 클레이·깊이·노멀 맵 포함)를 Nano Banana, ChatGPT, ComfyUI, Midjourney 등 AI 그림 도구의 포즈 참고로 바로 쓸 수 있습니다.**
[English](../../README.md) · [简体中文](README.zh-CN.md) · [日本語](README.ja.md) · 한국어
@@ -25,7 +25,7 @@
> **콘텐츠 안내:** 전신・섹시와 2인 시리즈는 다소 선정적인 성인용 포즈 참고입니다(마네킹, 노출 묘사 없음). 미리보기와 검색용 페이지에는 넣지 않으며, 갤러리에서는 기본으로 흐리게 보이며, 하나씩 탭하거나 스위치를 켜면 볼 수 있습니다.
-[![Shisei 갤러리: 카테고리 색 타일 위에 마네킹 포즈가 늘어선 첫 화면](../screenshot.png)](https://shisei.indaloop.app/ko/)
+[![Shisei 갤러리: 카테고리 색 타일 위 선화 사이로 클레이·깊이·노멀 맵이 섞여 흐르는 첫 화면](../screenshot.png)](https://shisei.indaloop.app/ko/)
Shisei는 직접 만든 포즈 참고 라이브러리입니다. 모든 포즈는 얼굴 없는 마네킹으로, 정면·사선·측면·위에서·아래에서의 다섯 앵글로 그렸습니다. 필요한 카메라 위치의 한 장을 그대로 이미지 모델에 넣으면 됩니다. 포즈 이름과 카테고리는 일본어·중국어·영어·한국어 네 가지 언어로 제공합니다.
@@ -60,7 +60,7 @@ Shisei는 직접 만든 포즈 참고 라이브러리입니다. 모든 포즈는
| `w900` | `images/*/w900/` | 900 × 1200 | 약 29 KB |
| 원본 | [원본 zip](#다운로드) | 1344 × 1792 (실사 1120 × 2240, 다시 그린 세트 900 × 1200) | 약 100 KB |
-저장소에는 웹용 세 가지 크기(약 63 MB)만 두므로 클론이 가볍습니다. 원본과 묶음 zip은 [Releases](https://github.com/wquguru/shisei/releases) 페이지에 있습니다.
+저장소에는 웹용 세 가지 크기를 둡니다(포즈는 선화·실사·클레이·깊이·노멀로 약 145 MB, 그 밖에 의상 라이브러리가 약 150 MB). 대부분은 zip만 있으면 됩니다. 원본과 묶음 zip은 [Releases](https://github.com/wquguru/shisei/releases) 페이지에 있습니다.
### 다운로드
diff --git a/docs/readme/README.zh-CN.md b/docs/readme/README.zh-CN.md
index 041489af..7d16fb7d 100644
--- a/docs/readme/README.zh-CN.md
+++ b/docs/readme/README.zh-CN.md
@@ -25,7 +25,7 @@
> **内容提示:**全身・性感和双人系列是偏性感的成人姿势参考(素体人偶,无裸露细节),不进预览和搜索页面,图库里默认模糊显示,点单张或打开开关才看得清。
-[![Shisei 画廊:首屏是一排排彩色分类色块上的素体姿势](../screenshot.png)](https://shisei.indaloop.app/)
+[![Shisei 画廊:首屏是一排排彩色色块上的素体线稿,夹着白模、深度图和法线图](../screenshot.png)](https://shisei.indaloop.app/)
Shisei 是一套自己生成的姿势参考库。每个姿势都是无脸素体,画了正面、斜侧、侧面、俯视、仰视五个机位,需要哪个角度就拿哪张喂给模型。姿势名和分类有日、中、英、韩四种语言。
@@ -60,7 +60,7 @@ Shisei 是一套自己生成的姿势参考库。每个姿势都是无脸素体
| `w900` | `images/*/w900/` | 900×1200 | 29 KB |
| 原图 | [原图包](#下载) | 1344×1792(实拍 1120×2240,重画的套 900×1200) | 100 KB |
-仓库里只放网页用的三档,约 63 MB,克隆会快很多。原图和打好的压缩包在 [Releases](https://github.com/wquguru/shisei/releases) 页面。
+仓库里放的是网页用的三档:姿势约 145 MB(线稿、实拍和白模、深度、法线),另有服装库约 150 MB。大多数人下压缩包就够了。原图和打好的压缩包在 [Releases](https://github.com/wquguru/shisei/releases) 页面。
### 下载
diff --git a/docs/screenshot.png b/docs/screenshot.png
index 8b31504c..abb6fc99 100644
Binary files a/docs/screenshot.png and b/docs/screenshot.png differ
diff --git a/web/i18n.js b/web/i18n.js
index ec0d8b70..834489ef 100644
--- a/web/i18n.js
+++ b/web/i18n.js
@@ -6,7 +6,7 @@ window.I18N = {
navHow: '使用方法',
madeTag: '方法论', madeText: '21 小时从零做出这套图库',
langLabel: '切换语言', theme: '切换深色模式',
- heroTitle: ['姿势线稿参考', '五机位'],
+ heroTitle: ['姿势参考', '五机位'],
heroSub: (n, v) => n + ' 套无脸素体姿势、' + v + ' 张线稿,正面、斜侧、侧面、俯视、仰视最多五个机位;大部分机位另有白模、深度图和法线图。拖进你的 AI 绘图工具,姿势就定住了。',
browse: (n) => '浏览 ' + n + ' 套姿势', downloadAll: '下载图包', worksWith: '适用于',
allTitle: '全部姿势', all: '全部', angleAll: '全部机位',