NSFW images detection ai

Adult content detection technology identifies explicit content in images that are not safe for work or other public places.
Our AI model detects exposed parts of a body and classifies if they are considered NSFW content.

Detection configuration

confidence threshold of when the detected region is used
typically a threshold of 0.25~0.5 should be a good range to reliably detect a category,
setting this to a high value means that it will only trigger censoring when it’s more confident, setting it to 1 is the same as disabling a category, on the other hand setting a low value would make censoring easier to trigger but also more chance of erroneously detecting regions

List of categories

• covered_genitalia_female
• face_female
• exposed_buttocks
• exposed_breast_female
• exposed_genitalia_female
• exposed_breast_male
• exposed_anus
• exposed_feet
• covered_belly
• covered_feet
• covered_armpits
• exposed_armpits
• face_male
• exposed_belly
• exposed_genitalia_male
• covered_anus
• covered_breast_female
• covered_buttocks

Default category configuration

The exposed_breast_female, exposed_genitalia_female, exposed_anus, exposed_genitalia_male categories default to 0.25, all others default to 1 (equivalent to being disabled).

Filter types

Gaussian Blur: Blur the image control with Blur strength
Variable blur: Applies varying strength blur strength based of the grayscale value of the mask, making the censor border less eye jarring.
Pixelate: Pixelated Mosaic effect.
Fill color: Fill a specified color

Mask shape

The mask shape applied on the detected regions.
Rectangle (default), Ellipse, Rounded rectangle, Entire image, Rectangle border

Fill color

Fill the detected region with this color or border color for mask shape Rectangle border

Rectangle border width

Border width for mask shape Rectangle border

Endpoints

Method:

POST

Endpoint:

/nsfw-from-url

Query params:

covered_genitalia_female: NUMBER (range 0-1)
face_female: NUMBER (range 0-1)
exposed_buttocks: NUMBER (range 0-1)
exposed_breast_female: NUMBER (range 0-1)
exposed_genitalia_female: NUMBER (range 0-1)
exposed_breast_male: NUMBER (range 0-1)
exposed_anus: NUMBER (range 0-1)
exposed_feet: NUMBER (range 0-1)
covered_belly: NUMBER (range 0-1)
covered_feet: NUMBER (range 0-1)
covered_armpits: NUMBER (range 0-1)
exposed_armpits: NUMBER (range 0-1)
face_male: NUMBER (range 0-1)
exposed_belly: NUMBER (range 0-1)
exposed_genitalia_male: NUMBER (range 0-1)
covered_anus: NUMBER (range 0-1)
covered_breast_female: NUMBER (range 0-1)
covered_buttocks: NUMBER (range 0-1)

Body:

url: STRING (REQUIRED)
rectangle_border_width: NUMBER
fill_color: STRING
mask_shape: STRING (Rectangle (default), Ellipse, Rounded rectangle, Entire image, Rectangle border)
filter_type: STRING (Gaussian Blur, Fill color (default), Variable blur, Pixelate)

Response:

{
  image: string | null;
  mask: string | null;
}

if the area is not found, image and mask will return null.

---

Method:

POST

Endpoint:

/nsfw-from-file

Query params:

covered_genitalia_female: NUMBER (range 0-1)
face_female: NUMBER (range 0-1)
exposed_buttocks: NUMBER (range 0-1)
exposed_breast_female: NUMBER (range 0-1)
exposed_genitalia_female: NUMBER (range 0-1)
exposed_breast_male: NUMBER (range 0-1)
exposed_anus: NUMBER (range 0-1)
exposed_feet: NUMBER (range 0-1)
covered_belly: NUMBER (range 0-1)
covered_feet: NUMBER (range 0-1)
covered_armpits: NUMBER (range 0-1)
exposed_armpits: NUMBER (range 0-1)
face_male: NUMBER (range 0-1)
exposed_belly: NUMBER (range 0-1)
exposed_genitalia_male: NUMBER (range 0-1)
covered_anus: NUMBER (range 0-1)
covered_breast_female: NUMBER (range 0-1)
covered_buttocks: NUMBER (range 0-1)\

Body:

image: FILE (REQUIRED)
rectangle_border_width: NUMBER
fill_color: STRING
mask_shape: STRING (Rectangle (default), Ellipse, Rounded rectangle, Entire image, Rectangle border)
filter_type: STRING (Gaussian Blur, Fill color (default), Variable blur, Pixelate)

Response:

{
  image: string | null;
  mask: string | null;
}

if the area is not found, image and mask will return null.

Possible errors

While analyzing your content, you may encounter the errors listed below:

400 - Bad Request
500 - Internal Server Error

Use Cases

1. Forum Moderation: Automatically identify and handle explicit or offensive visuals to prevent users from posting inappropriate content in the forum.

2. Messaging Apps Security: Enhance security in messaging applications by restricting access to NSFW content and ensuring secure communication among users.

3. Comment Moderation: Quickly detect and filter out potentially offensive content in comments to maintain a safe and respectful environment in comment sections.

4. Digital Ads Management: Identify and block offensive or mature content in digital advertisements before they are published, using sophisticated image detection techniques.

5. E-commerce & Marketplaces Integrity: Create a safe and NSFW-free marketplace environment by automatically flagging adult content to protect your brand’s reputation and ensure user safety.

6. Dating Websites Safety: Ensure a secure space on dating websites by filtering out explicit or inappropriate content, safeguarding users from potential abusers and maintaining a positive user experience.

7. Stock Websites Content Management: Monitor user-generated content on stock websites to identify and prevent the sharing of potentially harmful material, enhancing platform safety and user trust.

8. Video Game Streaming Platforms Security: Utilize nudity detection APIs to detect and remove adult content in real-time video game streams, guaranteeing that only safe content is broadcasted to viewers.