NSFW Image Classifier Open-source Image Classification Model - Free for Content Moderation, Accurately Classify Image Categories

Nsfw Image Classifier

Developed by quentintaranpino

A FocalNet fine-tuned NSFW image classification model for content moderation tasks, categorizing images into safe, needs review, and unsafe classes.

Image Classification

Transformers

English#Adult content moderation #High-precision classification #FocalNet architecture

Downloads 199

Release Time : 2/16/2025

Model Overview

This model is an image classification model fine-tuned based on the FocalNet architecture, specifically designed to identify and classify Not Safe For Work (NSFW) content, suitable for content moderation scenarios.

Model Features

High-precision classification

Accurately classifies images into safe, needs review, and unsafe categories, suitable for content moderation.

Based on FocalNet architecture

Uses microsoft/focalnet-base as the base model, offering excellent image processing capabilities.

Fine-tuned with additional data

Incorporates additional image data provided by nostrcheck.me for fine-tuning, improving recognition accuracy and robustness.

Safe tensor format

The model adopts the safetensors format, ensuring security and compatibility.

Model Capabilities

Image classification

NSFW content detection

Content moderation

Use Cases

Content moderation

Social media content filtering

Automatically detects and filters inappropriate content on social media platforms.

Significantly reduces manual review workload and enhances content safety.

Adult content identification

Identifies and classifies adult or inappropriate content for further processing.

Improves platform content quality and protects users from exposure to inappropriate material.

🚀 NSFW Image Classification Model - Fine-Tuned FocalNet

This repository hosts a fine-tuned NSFW image classification model based on FocalNet, tailored for content moderation. It classifies images into Safe, Questionable, and Unsafe categories.

🚀 Quick Start

This repository contains a fine-tuned NSFW image classification model based on FocalNet, optimized for content moderation tasks. The model classifies images into three categories: Safe, Questionable, and Unsafe.

This model is an improved version of MichalMlodawski/nsfw-image-detection-large, which was originally built on microsoft/focalnet-base. It has been further fine-tuned with additional image data obtained from nostrcheck.me, enhancing its accuracy and robustness in identifying inappropriate content.

✨ Features

Enhanced Accuracy: Fine - tuned with extra data from nostrcheck.me for better performance in content moderation.
Multi - Category Classification: Classifies images into Safe, Questionable, and Unsafe categories.

📚 Documentation

Model Details

Property	Details
Base Model	`microsoft/focalnet-base`
Fine - Tuned From	`MichalMlodawski/nsfw-image-detection-large`
Architecture	`FocalNetForImageClassification`
Image Input Size	`224x224 pixels`
Classification Labels	Safe: Appropriate content; Questionable: Requires manual review; Unsafe: NSFW or inappropriate content
Training Framework	`PyTorch`
Model Format	`safetensors`

Limitations

⚠️ Important Note

The model is highly accurate but may still produce incorrect classifications (False Positives/Negatives).

It analyzes images in isolation, without considering accompanying text or metadata (Contextual Understanding).

This model is released under CC BY - NC - SA 4.0, which requires attribution, prohibits commercial use, and mandates sharing under the same license (License Restrictions).

📄 License

This model is released under the CC BY - NC - SA 4.0 license.

Acknowledgments

This model is a fine - tuned version of MichalMlodawski/nsfw-image-detection-large, originally trained on microsoft/focalnet-base. Additional training data was obtained from nostrcheck.me to further improve its performance.

References

This model is part of an ongoing effort to improve content moderation through AI. Contributions and feedback are welcome.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご