Skip to content

Commit ae00f60

Browse files
MatrixAMatrixA
authored
docs: make Chinese README the default (#19)
1 parent 8077b39 commit ae00f60

8 files changed

Lines changed: 275 additions & 93 deletions

File tree

‎README.md‎

Lines changed: 75 additions & 75 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,10 @@
1-
> **English** | [简体中文](docs/README.zh-CN.md) | [Deutsch](docs/README.de.md) | [日本語](docs/README.ja.md) | [한국어](docs/README.ko.md) | [हिन्दी](docs/README.hi.md) | [Español](docs/README.es.md)
1+
> [English](docs/README.en.md) | **简体中文** | [Deutsch](docs/README.de.md) | [日本語](docs/README.ja.md) | [한국어](docs/README.ko.md) | [हिन्दी](docs/README.hi.md) | [Español](docs/README.es.md)
22
33
<div align="center">
44

55
# AICheck
66

7-
**Detect AI-generated content. Offline. No API keys. No setup.**
7+
**检测 AI 生成的内容。离线运行。无需 API key。无需配置。**
88

99
[![CI](https://github.com/MatrixA/aicheck/actions/workflows/ci.yml/badge.svg)](https://github.com/MatrixA/aicheck/actions/workflows/ci.yml)
1010
[![Crates.io](https://img.shields.io/crates/v/aicheck)](https://crates.io/crates/aicheck)
@@ -13,25 +13,25 @@
1313

1414
</div>
1515

16-
*That viral image — AI or real?*
17-
*Which model generated this video?*
18-
*Can you trust this photo's metadata?*
16+
*那张疯传的图片——是 AI 还是真的？*
17+
*这个视频是用哪个模型生成的？*
18+
*这张照片的元数据可信吗？*
1919

20-
AICheck answers these questions by analyzing file metadata and invisible watermarks. No API keys, no network, no setup.
20+
AICheck 通过分析文件元数据和隐形水印来回答这些问题。不需要 API key，不需要联网，不需要配置。
2121

22-
**10 detection methods** · **61 AI tools** · **16 file formats** · **3 confidence tiers** · **Zero network requests**
22+
**10 种检测方法** · **61 种 AI 工具** · **16 种文件格式** · **3 级置信度** · **完全离线运行**
2323

24-
[![Demo Video](https://img.youtube.com/vi/1u-6TkHtWiA/maxresdefault.jpg)](https://youtu.be/1u-6TkHtWiA)
24+
[![演示视频（Bilibili）](https://img.youtube.com/vi/1u-6TkHtWiA/maxresdefault.jpg)](https://www.bilibili.com/video/BV16Mc6zAE1s)
2525

2626
---
2727

28-
## ⚡ Quick Start
28+
## ⚡ 快速开始
2929

3030
```bash
3131
cargo install aicheck
3232
```
3333

34-
> Requires [Rust 1.86+](https://rust-lang.org/tools/install/). Or build from source: `cargo install --path .`
34+
> 需要 [Rust 1.86+](https://rust-lang.org/tools/install/)。从源码构建：`cargo install --path .`
3535
3636
```bash
3737
aic check photo.jpg
@@ -50,131 +50,131 @@ real_photo.jpg
5050

5151
---
5252

53-
## 🔍 How It Works
53+
## 🔍 工作原理
5454

5555
```
56-
your file
56+
你的文件
5757
|
5858
+------+------+------+------+------+------+------+
5959
| | | | | | | |
6060
v v v v v v v v
61-
[C2PA] [XMP] [EXIF] [PNG] [MP4] [ID3] [WAV] [FILE]
61+
[C2PA] [XMP] [EXIF] [PNG] [MP4] [ID3] [WAV] [文件名]
6262
HIGH MEDIUM LOW LOW MEDIUM MEDIUM MEDIUM LOW
6363
| | | | | | | |
6464
+--+---+--+---+--+---+--+---+--+---+--+---+--+---+
6565
| |
6666
v v
67-
metadata signals found? no signals?
67+
检测到元数据信号? 没有信号?
6868
| |
6969
v v
70-
[ Verdict ] [ Invisible Watermark / Audio Spectral ]
71-
DWT-DCT or FFT analysis
72-
confidence: LOW
70+
[ 判定 ] [ 隐形水印 / 音频频谱分析 ]
71+
DWT-DCT 或 FFT 分析
72+
置信度: LOW
7373
|
7474
v
75-
[ Verdict ]
75+
[ 判定 ]
7676
```
7777

78-
### Detection Methods
78+
### 检测方法
7979

80-
**C2PA Manifests (HIGH confidence)** — Cryptographically signed provenance. If a C2PA manifest says "made by DALL-E," that's the most authoritative signal metadata can provide. Reads `digitalSourceType` and `claim_generator`. Works on images, videos, and audio (e.g. ElevenLabs).
80+
**C2PA 清单（HIGH 置信度）**— 经过加密签名的来源证明。如果 C2PA 清单写着「由 DALL-E 生成」，这就是元数据能提供的最权威证据。读取 `digitalSourceType` 和 `claim_generator` 字段。支持图片、视频和音频（如 ElevenLabs）。
8181

82-
**XMP/IPTC Metadata (MEDIUM confidence)** — Standard photo metadata: `DigitalSourceType`, `AISystemUsed`, `AIPromptInformation`, `CreatorTool`. Reliable but unsigned — can be faked or stripped.
82+
**XMP/IPTC 元数据（MEDIUM 置信度）**— 标准照片元数据：`DigitalSourceType`、`AISystemUsed`、`AIPromptInformation`、`CreatorTool`。可靠但没有签名——可以伪造或删除。
8383

84-
**MP4 Container Metadata (MEDIUM confidence)** — Parses iTunes-style atoms (`©too`, `©swr`), AIGC labels (China standard with JSON `ProduceID`), and H.264 SEI watermark markers (Kling, Sora, Runway, Pika, Luma, Hailuo, Pixverse, Vidu, Genmo, Haiper). Also detects non-AI creation software (FFmpeg, Remotion, Premiere, etc.) for informational display. Catches AI signals baked into video containers that other methods miss.
84+
**MP4 容器元数据（MEDIUM 置信度）**— 解析 iTunes 风格原子（`©too`、`©swr`）、AIGC 标签（中国标准，含 JSON `ProduceID`）和 H.264 SEI 水印标记（Kling、Sora、Runway、Pika、Luma、Hailuo、Pixverse、Vidu、Genmo、Haiper）。同时检测非 AI 创作软件（FFmpeg、Remotion、Premiere 等）作为信息展示。能捕获嵌入视频容器中的 AI 信号。
8585

86-
**ID3 Audio Metadata (MEDIUM confidence)** — Reads ID3v2 tags from MP3 files: comment frames (COMM), URL frames (WOAS/WOAF/WXXX), and text frames (TENC/TPUB/TXXX). Detects AI audio platforms like Suno (via embedded URLs and "made with suno" comments).
86+
**ID3 音频元数据（MEDIUM 置信度）**— 读取 MP3 文件的 ID3v2 标签：注释帧（COMM）、URL 帧（WOAS/WOAF/WXXX）和文本帧（TENC/TPUB/TXXX）。可检测 Suno 等 AI 音频平台（通过嵌入的 URL 和「made with suno」注释）。
8787

88-
**WAV Container Metadata (MEDIUM/LOW confidence)** — Parses RIFF LIST/INFO chunks (ISFT, ICMT, IART) for AI tool references. Also flags TTS-typical audio characteristics: mono channel + non-standard sample rates (16kHz, 22050Hz, 24000Hz).
88+
**WAV 容器元数据（MEDIUM/LOW 置信度）**— 解析 RIFF LIST/INFO 块（ISFT、ICMT、IART）中的 AI 工具引用。同时标记 TTS 典型音频特征：单声道 + 非标准采样率（16kHz、22050Hz、24000Hz）。
8989

90-
**EXIF Heuristics (LOW confidence)** — If the `Software` tag matches a known AI tool AND typical camera fields (Make, Model, GPS, focal length) are absent, it's likely AI-generated. Also detects hash-like Artist tags.
90+
**EXIF 启发式（LOW 置信度）**— 如果 `Software` 标签匹配已知 AI 工具，且缺少典型的相机字段（Make、Model、GPS、焦距），那大概率是 AI 生成的。也能检测哈希式的 Artist 标签。
9191

92-
**PNG Text Chunks (LOW confidence)** — Scans `tEXt` and `iTXt` chunks for AI tool references in Software, Comment, Description, Source, Author, parameters, and prompt keywords.
92+
**PNG 文本块（LOW 置信度）**— 扫描 `tEXt` 和 `iTXt` 块中 Software、Comment、Description、Source、Author、parameters、prompt 等关键字里的 AI 工具引用。
9393

94-
**Filename Patterns (LOW confidence)** — Matches filenames against known AI tool naming conventions (e.g. ElevenLabs timestamp format `ElevenLabs_YYYY-MM-DDTHH_MM_SS_*`, Suno/SoundRaw prefixes, Midjourney/DALL-E in filenames).
94+
**文件名模式（LOW 置信度）**— 将文件名与已知 AI 工具的命名规则匹配（如 ElevenLabs 的时间戳格式 `ElevenLabs_YYYY-MM-DDTHH_MM_SS_*`、Suno/SoundRaw 前缀、文件名中的 Midjourney/DALL-E）。
9595

96-
**Audio Spectral Analysis (LOW confidence)** — FFT-based analysis of WAV audio: detects hard frequency cutoffs (energy concentrated below Nyquist) and abnormal spectral flatness typical of TTS/AI synthesis. Runs as a fallback or with `--deep`.
96+
**音频频谱分析（LOW 置信度）**— 基于 FFT 的 WAV 音频分析：检测硬频率截断（能量集中在奈奎斯特频率以下）和异常的频谱平坦度，这些是 TTS/AI 合成的典型特征。作为后备方案自动运行，或通过 `--deep` 强制启用。
9797

98-
**Invisible Watermarks (LOW confidence)** — Pixel-level DWT-DCT analysis that detects channel noise asymmetry, cross-channel bit agreement, and wavelet energy patterns. For videos, automatically extracts keyframes via `ffmpeg` and analyzes them individually. Runs automatically as a fallback when no metadata signals are found, or on demand with `--deep`.
98+
**隐形水印（LOW 置信度）**— 像素级 DWT-DCT 分析，检测通道噪声不对称性、跨通道比特一致性和小波能量模式。对于视频文件，自动通过 `ffmpeg` 提取关键帧并逐帧分析。当未检测到元数据信号时自动运行，也可通过 `--deep` 强制启用。
9999

100100
---
101101

102-
## 🎯 What It Recognizes
102+
## 🎯 识别能力
103103

104-
### AI Tools
104+
### AI 工具
105105

106-
| Category | Tools |
107-
|----------|-------|
108-
| Image generation | DALL-E, Midjourney, Stable Diffusion, Adobe Firefly, Imagen, Flux, Ideogram, Leonardo.ai, NovelAI, Grok, Jimeng (即梦) |
109-
| Video generation | Sora, Google Veo, Runway, Pika, Kling, Vidu, Luma, Hailuo (海螺), Pixverse, Genmo, Haiper |
110-
| Audio/Music generation | Suno, Udio, ElevenLabs, SoundRaw, AIVA, Boomy, Mubert, Beatoven, Soundful, Hume, Fish Audio |
111-
| Multimodal | GPT-4o, GPT-4, ChatGPT, OpenAI, GPT Image, Gemini |
112-
| Platforms | Bing Image Creator, Copilot Designer, Microsoft Designer, Canva AI, DreamStudio, NightCafe, Craiyon, DeepAI, Meta AI, Stability AI |
113-
| Interfaces | ComfyUI, Automatic1111 (A1111), InvokeAI, Fooocus |
114-
| Research | Glide, Parti, Muse, Seedream, Recraft |
106+
| 类别 | 工具 |
107+
|------|------|
108+
| 图像生成 | DALL-E, Midjourney, Stable Diffusion, Adobe Firefly, Imagen, Flux, Ideogram, Leonardo.ai, NovelAI, Grok, Jimeng (即梦) |
109+
| 视频生成 | Sora, Google Veo, Runway, Pika, Kling, Vidu, Luma, Hailuo (海螺), Pixverse, Genmo, Haiper |
110+
| 音频/音乐生成 | Suno, Udio, ElevenLabs, SoundRaw, AIVA, Boomy, Mubert, Beatoven, Soundful, Hume, Fish Audio |
111+
| 多模态 | GPT-4o, GPT-4, ChatGPT, OpenAI, GPT Image, Gemini |
112+
| 平台 | Bing Image Creator, Copilot Designer, Microsoft Designer, Canva AI, DreamStudio, NightCafe, Craiyon, DeepAI, Meta AI, Stability AI |
113+
| 界面工具 | ComfyUI, Automatic1111 (A1111), InvokeAI, Fooocus |
114+
| 研究项目 | Glide, Parti, Muse, Seedream, Recraft |
115115

116-
### File Formats
116+
### 文件格式
117117

118-
| Type | Formats |
119-
|------|---------|
120-
| Image | JPEG, PNG, WebP, AVIF, HEIF, TIFF, GIF, BMP |
121-
| Video | MP4, MOV, AVI, WebM |
122-
| Audio | MP3, M4A, WAV |
123-
| Document | PDF |
118+
| 类型 | 格式 |
119+
|------|------|
120+
| 图片 | JPEG, PNG, WebP, AVIF, HEIF, TIFF, GIF, BMP |
121+
| 视频 | MP4, MOV, AVI, WebM |
122+
| 音频 | MP3, M4A, WAV |
123+
| 文档 | PDF |
124124

125125
---
126126

127-
## 💻 Commands
127+
## 💻 命令
128128

129129
### `aic check [PATHS]`
130130

131-
Analyze files for AI-generation signals.
131+
分析文件中的 AI 生成信号。
132132

133133
```bash
134-
aic check photo.jpg # single file
135-
aic check images/ -r # directory, recursive
136-
aic check photo.jpg --json # JSON output
137-
aic check photo.jpg -q # quiet — exit code only
138-
aic check photo.jpg --min-confidence medium # filter by confidence
139-
aic check photo.jpg --deep # force pixel-level watermark analysis
134+
aic check photo.jpg # 单个文件
135+
aic check images/ -r # 目录，递归扫描
136+
aic check photo.jpg --json # JSON 输出
137+
aic check photo.jpg -q # 静默模式——仅返回退出码
138+
aic check photo.jpg --min-confidence medium # 按置信度过滤
139+
aic check photo.jpg --deep # 强制启用像素级水印分析
140140
```
141141

142142
### `aic info <FILE>`
143143

144-
Dump all provenance metadata (C2PA manifests, XMP properties, EXIF fields, MP4 atoms, ID3 tags, WAV metadata, watermark analysis).
144+
输出所有溯源元数据（C2PA 清单、XMP 属性、EXIF 字段、MP4 原子、ID3 标签、WAV 元数据、水印分析）。
145145

146146
```bash
147147
aic info photo.jpg
148148
```
149149

150-
### Global Flags
150+
### 全局选项
151151

152-
| Flag | Effect |
153-
|------|--------|
154-
| `--json` | Output as JSON |
155-
| `-q, --quiet` | Suppress output, set exit code only |
156-
| `--deep` | Force invisible watermark and audio spectral analysis on all files |
157-
| `--no-color` | Disable colored output |
152+
| 选项 | 说明 |
153+
|------|------|
154+
| `--json` | 以 JSON 格式输出 |
155+
| `-q, --quiet` | 不输出内容，仅设置退出码 |
156+
| `--deep` | 强制对所有文件进行隐形水印和音频频谱分析 |
157+
| `--no-color` | 禁用彩色输出 |
158158

159-
### Exit Codes
159+
### 退出码
160160

161-
| Code | Meaning |
162-
|------|---------|
163-
| `0` | AI signals detected |
164-
| `1` | No AI signals |
165-
| `2` | Error |
161+
| 退出码 | 含义 |
162+
|--------|------|
163+
| `0` | 检测到 AI 信号 |
164+
| `1` | 未检测到 AI 信号 |
165+
| `2` | 错误 |
166166

167167
---
168168

169-
## ⚠️ Limitations
169+
## ⚠️ 局限性
170170

171-
- **Stripped metadata = invisible.** If someone removes the metadata, there's nothing to detect. Social platforms do this on upload — always analyze the original file.
172-
- **Most AI images have no watermark.** Only ~19% of AI images carry detectable provenance markers (2025 data).
173-
- **Proprietary watermarks are out of reach.** SynthID, Stable Signature, and VideoSeal require keys we don't have.
174-
- **Pixel-level analysis has limits.** The built-in DWT-DCT watermark detector catches common patterns but is not a full forensic classifier. For deep statistical detection, use dedicated forensic tools.
171+
- **元数据被删了就没辙。** 如果有人把元数据剥掉了，那就没有可检测的内容。社交平台上传时会自动做这件事——请分析原始文件。
172+
- **大多数 AI 图片没有水印。** 仅约 19% 的 AI 图片携带可检测的来源标记（2025 年数据）。
173+
- **专有水印无法识别。** SynthID、Stable Signature、VideoSeal 需要我们没有的密钥。
174+
- **像素级分析有局限。** 内置的 DWT-DCT 水印检测器能捕获常见模式，但不是完整的取证分类器。深度统计检测请使用专业取证工具。
175175

176176
---
177177

178-
## 📄 License
178+
## 📄 许可证
179179

180180
[AGPL-3.0](LICENSE)

‎docs/README.de.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
> [English](../README.md) | [简体中文](README.zh-CN.md) | **Deutsch** | [日本語](README.ja.md) | [한국어](README.ko.md) | [हिन्दी](README.hi.md) | [Español](README.es.md)
1+
> [English](README.en.md) | [简体中文](../README.md) | **Deutsch** | [日本語](README.ja.md) | [한국어](README.ko.md) | [हिन्दी](README.hi.md) | [Español](README.es.md)
22
33
<div align="center">
44

@@ -8,7 +8,7 @@
88

99
[![CI](https://github.com/MatrixA/aicheck/actions/workflows/ci.yml/badge.svg)](https://github.com/MatrixA/aicheck/actions/workflows/ci.yml)
1010
[![Crates.io](https://img.shields.io/crates/v/aicheck)](https://crates.io/crates/aicheck)
11-
[![License: AGPL-3.0](https://img.shields.io/badge/license-AGPL--3.0-blue.svg)](LICENSE)
11+
[![License: AGPL-3.0](https://img.shields.io/badge/license-AGPL--3.0-blue.svg)](../LICENSE)
1212
[![Rust](https://img.shields.io/badge/rust-1.86%2B-orange.svg)](https://www.rust-lang.org/)
1313

1414
</div>
@@ -175,4 +175,4 @@ aic info photo.jpg
175175

176176
## 📄 Lizenz
177177

178-
[AGPL-3.0](LICENSE)
178+
[AGPL-3.0](../LICENSE)

0 commit comments

Comments
 (0)