Solution for checking if images contain NSFW content.
10K+
This is an NSFW content detector based on Falconsai/nsfw_image_detection.
Model: google/vit-base-patch16-224-in21k
You can try it online(using Public API): NSFW Detector
Compared to other common NSFW detectors, this detector has the following advantages:
Running this model requires up to 2GB of memory. No GPU support is needed.
When handling a large number of requests simultaneously, more memory may be required.
This detector supports checking the following file types:
docker run -d -p 3333:3333 --name nsfw-detector vxlink/nsfw_detector:latest
To check files in local paths on the server, mount the path to the container. It is recommended to keep the mounted path consistent with the path inside the container to avoid confusion.
docker run -d -p 3333:3333 -v /path/to/files:/path/to/files --name nsfw-detector vxlink/nsfw_detector:latest
Supported architectures: x86_64, ARM64.
# Detection
curl -X POST -F "file=@/path/to/image.jpg" http://localhost:3333/check
# Check Local Files
curl -X POST -F "path=/path/to/image.jpg" http://localhost:3333/check
Visit: http://localhost:3333
Now, you can configure the detector's behavior by mounting the /tmp directory and creating a file named config in that directory. You can refer to the config file as a reference.
nsfw_threshold Sets what NSFW value threshold must be exceeded for a target file to be considered a match and returned as a result.ffmpeg_max_frames Maximum number of frames to process when handling videos.ffmpeg_max_timeout Timeout limit when processing videos.Additionally, since the /tmp directory serves as a temporary directory in the container, configuring it on a high-performance storage device will improve performance.
You can use the public API service provided by vx.link.
# Detect files, automatically recognize file types
curl -X POST -F "file=@/path/to/image.jpg" https://vx.link/public/nsfw
This project is open-source under the Apache 2.0 license.
Content type
Image
Digest
sha256:00526a58b…
Size
1.5 GB
Last updated
over 1 year ago
docker pull vxlink/nsfw_detector