Deepfake detectionComputer visionDocuments and OCR

TruFor

Finds traces of editing and shows on a map which regions of an image look altered: suitable for scans of contracts, certificates and photos of documents. It errs in both directions - a person decides.

Developer
GRIP, University Federico II of Naples, Italy
First release
Dec 2022
Latest release
May 2025
Sizes
a transformer model producing a map of suspicious regions
License
Non-commercial onlyall rights reserved: use for informational and non-profit purposes only
Running
On your own serverNeeds a GPU
Industries
Security, Documents and accounting, Legal, Finance
Deploy on your server GitHub

What it does

  • Checking scans of certificates and contracts for edits
  • Highlighting altered photo regions for an expert
  • Filtering out obviously redrawn documents before manual review
  • Research into document-check quality

Where it is used

Information securityDocument management and accountingLegal and complianceInsurance and banks

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. Текущие обновления репозитория
  2. Код обучения
  3. Код и веса для проверки
  4. TruFor (статья)

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 TruFor be used in a commercial project?

No. License: all rights reserved: use for informational and non-profit purposes only. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does TruFor 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 TruFor support Russian?

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

Where can I download TruFor and what does it cost?

The TruFor 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 detectionIML-ViTSichuan University and co-authors · ChinaCommercial use allowed

An open model for finding forgeries in images: it outputs a pixel-level mask of altered regions. It errs in both directions; its map is a hint for an expert, not proof of a forgery.

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.

DetailsDeepfake 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.

Details

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