> ## Documentation Index
> Fetch the complete documentation index at: https://cloudinary.com/documentation/llms.txt
> Use this file to discover all available pages before exploring further.

# Moderate images with AI (video tutorial)

## Overview

Moderate images automatically during upload by applying AI using Cloudinary and Amazon Rekognition, in Node.js.

 

## Video tutorial

  This video is brought to you by Cloudinary's video player - embed your own!Use the controls to set the playback speed, navigate to chapters of interest and select subtitles in your preferred language.

## Tutorial contents
This tutorial presents the following topics. Click a timestamp to jump to that part of the video.### Automatic image moderation
{table:class=tutorial-bullets}|  | 
| --- | --- |
|{videotime:id=media :min=0 :sec=00 :player=cld} | When you have thousands of images being uploaded to your site, moderating them manually isn't feasible. Instead, you can moderate them automatically using AI.
|

### Manual image moderation
{table:class=tutorial-bullets}|  | 
| --- | --- |
|{videotime:id=media :min=0 :sec=14 :player=cld} | When using the [Node.js SDK](node_integration) upload call to upload an image, you can set the `moderation` parameter to `manual` (as shown below). This sets the `moderation` status to `pending` in the upload response. You can find assets pending manual moderation in the Cloudinary Console, in the **Moderation** page of the **Media Library**, with **Manual** selected. There, you can manually approve or reject the assets.
|

```nodejs
const results = await cloudinary.uploader.upload("./images/food.jpg", {
  moderation: "manual"
});
```

### Image moderation using Amazon Rekognition
{table:class=tutorial-bullets}|  | 
| --- | --- |
|{videotime:id=media :min=1 :sec=13 :player=cld} | To moderate images automatically using Amazon Rekognition, first subscribe to the [Amazon Rekognition AI Moderation add-on](aws_rekognition_ai_moderation_addon), then set `moderation` to `aws_rek`. There are various [moderation categories](aws_rekognition_ai_moderation_addon#moderation_categorization) that you can [set thresholds for](aws_rekognition_ai_moderation_addon#request_image_moderation) in the upload call. Images are approved or rejected automatically based on the confidence threshold of the detected content. They are set to a 0.5 threshold by default.
|

```nodejs
const results = await cloudinary.uploader.upload("./images/food.jpg", {
  moderation: "aws_rek"
});
```

### Set automatic moderation in an upload preset
{table:class=tutorial-bullets}|  | 
| --- | --- |
|{videotime:id=media :min=2 :sec=15 :player=cld} | You can use an [upload preset](upload_presets) to configure automatic moderation. In the **Upload** settings of your product environment, you can create an upload preset with **Amazon Rekognition** set and you can fine-tune the category thresholds to suit your needs.
|
## Keep learning

> **READING**:
>
> * Read all about the [Amazon Rekognition AI Moderation](aws_rekognition_ai_moderation_addon) addon.

> * Read this [blog post](https://cloudinary.com/blog/how_to_automate_image_moderation_with_amazon_rekognition) for more insights on using Amazon Rekognition to moderate images.

> * Take a look at the [User-generated content guide](user_generated_content) to see all the features you can take advantage of when uploading images and videos to display on your site.

> * Watch more [Dev Hints videos](https://www.youtube.com/playlist?list=PL8dVGjLA2oMpaTbvoKCaRNBMQzBUIv7N8) on the [Cloudinary YouTube channel](https://www.youtube.com/cloudinary).

#### If you like this, you might also like...

  
  
  
    Upload Programmatically
    Use a Cloudinary SDK to upload media assets 
  

  
  
  
    Create Upload Presets (Node.js)
    Streamline media uploads using signed upload presets 
  

  
  
  
    Auto-Tag Images in Node.js
    Tag assets automatically during upload with AI in Node.js 
  

 

 Check out the Cloudinary Academy for free self-paced Cloudinary courses on a variety of developer or DAM topics, or register for formal instructor-led courses, either virtual or on-site.