Deepfake detectionComputer vision

UniversalFakeDetect

An early and still used approach: a simple classifier trained on top of a frozen CLIP that transfers to unseen generators. It errs in both directions - the output needs a human check.

Developer
University of Wisconsin-Madison, USA
First release
Feb 2023
Latest release
Aug 2026
Sizes
a linear classifier on top of CLIP ViT-L/14
License
Commercial use allowedMIT
Running
On your own serverAlso runs without a GPU
Industries
Security, Media and production, Marketing and content, Science and research
Deploy on your server GitHub

What it does

  • Checking images from new, unfamiliar generators
  • A baseline when comparing detectors
  • Fast rollout of a check without training a large model
  • Research into detection robustness

Where it is used

Content moderationMedia and fact-checkingInformation securityResearch

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Обновления кода и весов
  2. UniversalFakeDetect (CVPR 2023)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

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 UniversalFakeDetect be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does UniversalFakeDetect 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 UniversalFakeDetect support Russian?

Language does not matter for this model: it does not work with text.

Where can I download UniversalFakeDetect and what does it cost?

The UniversalFakeDetect 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

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Deepfake detectionCommunity ForensicsUniversity of Michigan · USACommercial use allowed

A lightweight detector of generated images, trained on 2.7M samples from nearly 5000 different generators. It errs in both directions: the result is a reason for a human to check, not proof.

DetailsDeepfake detectionAIDEXiaohongshu, USTC and Shanghai Jiao Tong University · ChinaCommercial use with conditions

An AI-image detector made of several experts: some look at visual artifacts, others at noise. The hard Chameleon benchmark was released with it. It errs in both directions - a human reviews the result.

DetailsDeepfake detectionDeepfakeBenchThe Chinese University of Hong Kong, Shenzhen (SCLBD) · ChinaNon-commercial only

Dozens of open face-swap detectors for video and photo under one codebase with ready weights. A detector errs in both directions: its output is a reason for a human to check, not proof of a forgery.

Details

Source: github.com/WisconsinAIVision/UniversalFakeDetect. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.