AI Image Detection Tool

Batch process images with one click, removing AI traces through algorithms such as color quantization and noise injection to reduce the likelihood of detection.

Bug report

Browser execution mode: Your data is processed in your browser and is not uploaded to the server.

Speed and Stability: Processing speed depends on your device and browser. For large batch work, the desktop version may be more stable.

Loading tool, please wait...

If the online tool fails to load or run, try the desktop tool.https://tools.yikeaigc.com/

Tool Usage

Return to old version

Instructions

Software Usage Instructions

Import image resources: Click "Browse Files" to select one or more images, or click "Browse Folder" to batch import an entire directory. Check "Traverse Subdirectories" to automatically process images at all levels within the folder.
Set the save path: Select the output directory for the processed images. If "Traverse Subdirectories" is enabled, you can check "Keep Original Path Structure" to maintain the original folder hierarchy.
Configure processing algorithms: Adjust the parameters as needed to achieve the best trace-removal results:
- Image quantization: Adjust the number of colors. The smaller the value, the stronger the processing and the more noticeable the trace-removal effect.
- Gaussian blur/noise: Moderately increasing the blur radius or noise intensity can disrupt the microscopic textures generated by AI.
- Denoising and image quality: Use median filtering for denoising, and adjust brightness, contrast, and JPEG output quality.
Advanced options:
- Clean metadata: Enabled by default. Automatically removes sensitive information such as EXIF to protect privacy.
- Output format: Supports exporting as PNG, JPEG, WebP, or BMP.
- Multithreaded processing: Set the number of threads based on your computer configuration (4-8 threads recommended) to improve processing speed.
Start processing: Click the "Start Processing" button, and the software will automatically execute the task. The log area below will display the processing progress and results in real time.

FAQ

A: Image quantization can reduce the number of colors in an image and disrupt the smooth transitions and specific texture features produced when AI generates images. It is one of the core methods for removing AI traces.

A: It is recommended to try the default parameters first. If the detection result still indicates AI-generated content, you can appropriately lower the "Quantization Strength" value (the smaller the value, the stronger the effect) or increase the "Gaussian Noise" intensity.

A: Importing all common image formats is supported. Output supports PNG, JPEG, WebP, and BMP formats. We recommend using PNG to preserve the best detail, or JPEG for a smaller file size.

A: This is a necessary loss introduced to disrupt AI fingerprints. If it feels too blurry, try reducing the "Gaussian Blur" radius or disabling this option, while appropriately increasing the "Image Quantization" value.

A: Processing speed depends on the image resolution and computer performance. You can try increasing the "Number of Threads" (recommended to set it to the number of CPU cores), or disabling the "Denoise" feature, since the denoising algorithm is relatively computationally intensive.