Deepfake detectionComputer vision

IML-ViT

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.

The last open version came out in Mar 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Sichuan University and co-authors, China
First release
Jul 2023
Latest release
Mar 2024
Sizes
a Vision Transformer based model
License
Commercial use allowedMIT
Running
On your own serverNeeds a GPU
Industries
Security, Documents and accounting, Legal, Science and research
Deploy on your server GitHub

What it does

  • Finding pasted and erased fragments in photos
  • Checking document scans for edits
  • A baseline when comparing manipulation-localization models
  • Fine-tuning for your own document types

Where it is used

Information securityDocument managementLegal and complianceResearch

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. Обновлённые веса
  2. Код обучения
  3. IML-ViT (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 IML-ViT 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 IML-ViT 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 IML-ViT support Russian?

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

Where can I download IML-ViT and what does it cost?

The IML-ViT 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 detectionTruForGRIP, University Federico II of Naples · ItalyNon-commercial only

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.

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/SunnyHaze/IML-ViT. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.