NSFW-классификаторы (Falconsai, Freepik)
Small models that tell explicit images from regular ones. The Freepik model distinguishes four levels of explicitness. They run on a CPU.
- Developer
- Falconsai and Freepik, USA and Spain
- First release
- Oct 2023
- Latest release
- Apr 2025
- Sizes
- 86M
- License
- Commercial use allowedFalconsai — Apache 2.0, Freepik — MIT
- Running
- On your own serverAlso runs without a GPU
- Industries
- Security, Media and production, Retail and marketplaces
What it does
- Filtering user photos and avatars
- Checking generated images before publishing
- Labeling a media library
Where it is used
Hardware requirements
Versions
- Freepik nsfw_image_detector (EVA02, 4 уровня)
- Falconsai nsfw_image_detection (ViT)
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can NSFW-классификаторы (Falconsai, Freepik) be used in a commercial project?
Yes. License: Falconsai — Apache 2.0, Freepik — MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does NSFW-классификаторы (Falconsai, Freepik) need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does NSFW-классификаторы (Falconsai, Freepik) support Russian?
Language does not matter for this model: it does not work with text.
Where can I download NSFW-классификаторы (Falconsai, Freepik) and what does it cost?
The NSFW-классификаторы (Falconsai, Freepik) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Gemma-based filters: they check text for dangerous and offensive content, and ShieldGemma 2 checks images. Focused on English.
DetailsComputer visionSigLIP (наследник CLIP)Google · USACommercial use allowedModels that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.
DetailsSource: huggingface.co/Freepik/nsfw_image_detector. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


