跳到正文
TakoAPI
返回技能列表

deai-image

由 swaylq 提供

Git & GitHub
282下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Detect and remove AI fingerprints from AI-generated images.

描述

该技能的功能

CLI tool that applies a 7-stage pipeline to AI-generated images to reduce their detectability by AI image detectors. Strips EXIF and C2PA metadata, adds synthetic camera noise, adjusts color distribution, and recompresses the file. Works with output from Midjourney, DALL-E, Stable Diffusion, Flux, and other generators.

Combines metadata stripping, frequency pattern disruption, noise injection, and recompression in a single command rather than running separate tools for each step.

何时使用

  • Stripping C2PA metadata from DALL-E exports before sharing
  • Batch cleaning a folder of Midjourney images for a client portfolio
  • Testing how well different processing strengths bypass Hive or Illuminarty detectors
  • Removing generation metadata from AI art before uploading to stock sites
  • Converting AI-generated product shots to reduce detection flags on e-commerce platforms

示例工作流

输入

User asks: Remove AI fingerprints from my Midjourney portrait at medium strength

智能体
  1. 1

    Run deai.py on the input file with default medium strength

  2. 2

    Strip EXIF and C2PA metadata via ExifTool

  3. 3

    Add Poisson/Gaussian grain and adjust contrast and saturation

  4. 4

    Perform resize cycle and JPEG recompression to introduce natural artifacts

  5. 5

    Run a final metadata clean pass and write the output file

输出

Processed JPEG with 50-65% bypass rate against common AI detectors and metadata fully removed

前置要求

  • ImageMagick 7.0+
  • ExifTool

安装

clawhub install swaylq/deai-image

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接