Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
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.
When to use it
- 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
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Remove AI fingerprints from my Midjourney portrait at medium strength
- 1Run deai.py on the input file with default medium strength
- 2Strip EXIF and C2PA metadata via ExifTool
- 3Add Poisson/Gaussian grain and adjust contrast and saturation
- 4Perform resize cycle and JPEG recompression to introduce natural artifacts
- 5Run a final metadata clean pass and write the output file
Processed JPEG with 50-65% bypass rate against common AI detectors and metadata fully removed
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.