A simple JavaScript library to help you quickly identify unseemly images; all in the client's browser. NSFWJS isn't perfect, but it's pretty accurate (~90% from our test set of 15,000 test images)... and it's getting more accurate all the time.
Why would this be useful? Check out the announcement blog post.
The library categorizes image probabilities in the following 5 classes:
Drawing
- safe for work drawings (including anime)Hentai
- hentai and pornographic drawingsNeutral
- safe for work neutral imagesPorn
- pornographic images, sexual actsSexy
- sexually explicit images, not pornography
The demo is a continuous deployment source - Give it a go: http://nsfwjs.com/
With async/await
support:
import * as nsfwjs from 'nsfwjs'
const img = document.getElementById('img')
// Load model from my S3.
// See the section hosting the model files on your site.
const model = await nsfwjs.load()
// Classify the image
const predictions = await model.classify(img)
console.log('Predictions: ', predictions)
Without async/await
support:
import * as nsfwjs from 'nsfwjs'
const img = document.getElementById('img')
// Load model from my S3.
// See the section hosting the model files on your site.
nsfwjs.load().then(function(model) {
model.classify(img).then(function(predictions) {
// Classify the image
console.log('Predictions: ', predictions)
})
})
Before you can classify any image, you'll need to load the model. You should use the optional first parameter and load the model from your website, as explained in the install directions.
const model = nsfwjs.load('/path/to/model/directory/')
If you're using a model that needs an image of dimension other than 224x224, you can pass the size in the options parameter.
const model = nsfwjs.load('/path/to/different/model/', {size: 299})
Parameters
- optional URL to the
model.json
folder. - optional object with size property that your model expects.
Returns
- Ready to use NSFWJS model object
This function can take any browser-based image elements (<img>
, <video>
, <canvas>
) and returns an array of most likely predictions and their confidence levels.
// Return top 3 guesses (instead of all 5)
const predictions = await model.classify(img, 3)
Parameters
- Tensor, Image data, Image element, video element, or canvas element to check
- Number of results to return (default all 5)
Returns
- Array of objects that contain
className
andprobability
. Array size is determined by the second parameter in theclassify
function.
This function can take a browser-based image element (<img>
) that is a GIF, and returns an array of prediction arrays. It breaks a GIF into its frames and runs classify
on each with a given configuration. This can take a while, as GIFs are frequently hundreds of frames.
// Returns all predictions of each GIF frame
const framePredictions = await model.classifyGif(img)
If you're looking to update the user on status (e.g. progress bar) or change the number of top results per frame, then you can utilize the configuration parameter.
Example of passing a configuration:
// returns top 1 prediction of each GIF frame, and logs the status to console
const myConfig = {
topk: 1,
setGifControl: (gifControl) => console.log(gifControl),
onFrame: ({ index, totalFrames, predictions }) =>
console.log(index, totalFrames, predictions)
}
const framePredictions = await classifyGif(img, myConfig)
Parameters
- Image element to check
- Configuration object with the following possible key/values:
topk
- Number of results to return per frame (default all 5)setGifControl
- Function callback receives SuperGif object as an argument, allows a user to save it for later useonFrame
- Function callback on each frame - Param is an object with the following key/values:index
- the current GIF frame that was classified (starting at 1)totalFrames
- the complete number of frames for this GIF (for progress calculations)predictions
- an array of lengthtopk
, returning top results from classify
Returns
- Array of the same order as number of frames in GIF. Each index corresponding to that frame, an returns array of objects that contain
className
andprobability
; sorted by probability and limited by topk config parameter.
NSFWJS is powered by Tensorflow.JS as a peer dependency. If your project does not already have TFJS you'll need to add it.
# peer dependency
$ yarn add @tensorflow/tfjs
# install NSFWJS
$ yarn add nsfwjs
The magic that powers NSFWJS is the NSFW detection model. By default, this node module is pulling from my S3, but I make no guarantees that I'll keep that download link available forever. It's best for the longevity of your project that you download and host your own version of the model files. You can then pass the relative URL to your hosted files in the load
function. If you can come up with a way to bundle the model into the NPM package, I'd love to see a PR to this repo!
The demo that powers https://nsfwjs.com/ is available in the nsfw_demo
example folder.
To run the demo, run yarn prep
which will copy the latest code into the demo. After that's done, you can cd
into the demo folder and run with yarn start
.
A browserified version using nothing but promises and script tags is available in the minimal_demo
folder.
Please do not use the script tags hosted in this demo as a CDN. This can and should be hosted in your project along side the model files.
An FAQ page is available.
The model was trained in Keras over several days and 60+ Gigs of data. Be sure to check out the model code which was trained on data provided by Alexander Kim's nsfw_data_scraper.
NSFWJS, as open source, is free to use and always will be β€οΈ. It's MIT licensed, and we'll always do our best to help and quickly answer issues. If you'd like to get a hold of us, join our community slack.
Infinite Red offers premium training and support. Email us at hello@infinite.red to get in touch.
Thanks goes to these wonderful people (emoji key):
This project follows the all-contributors specification. Contributions of any kind welcome!