Deepfake detectionComputer vision

AIDE

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.

Developer
Xiaohongshu, USTC and Shanghai Jiao Tong University, China
First release
Jun 2024
Latest release
Jun 2025
Sizes
several experts based on ConvNeXt and CLIP
License
Commercial use with conditionsMIT for the code; the Chameleon dataset is research-only
Running
On your own serverNeeds a GPU
Industries
Security, Media and production, Marketing and content, Science and research
Deploy on your server GitHub

What it does

  • Checking realistic AI images without obvious artifacts
  • Comparing detectors on hard examples
  • Fine-tuning for your own type of content
  • Studying weak spots in detection

Where it is used

Platform moderationMedia and advertisingInformation securityResearch

Hardware requirements

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

Versions

  1. Обновления после ICLR 2025
  2. Набор данных Chameleon
  3. AIDE (статья и код)

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 AIDE be used in a commercial project?

With conditions. License: MIT for the code; the Chameleon dataset is research-only. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does AIDE need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does AIDE support Russian?

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

Where can I download AIDE and what does it cost?

The AIDE 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 detectionUniversalFakeDetectUniversity of Wisconsin-Madison · USACommercial use allowed

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.

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/shilinyan99/AIDE. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.