Deepfake detectionVideo

VideoSeal

A watermark for video and images that survives re-encoding and cropping. The detector errs in both directions: a missing mark does not prove a forgery, and finding one is a reason for a human to check.

Developer
Meta, USA
First release
Dec 2024
Latest release
Dec 2025
Sizes
a mark of 96 to 1024 bits
License
Commercial use allowedMIT
Running
On your own serverNeeds a GPU
Industries
Media and production, Security, Marketing and content, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Marking video created or processed by AI
  • Finding your own mark in re-uploaded clips
  • Protecting ad materials from being reused as someone else's
  • Tracing leaks of video material

Where it is used

Video production and mediaMarketing and advertisingInformation securityLegal departments

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. ChunkySeal (1024 бита)
  2. PixelSeal (256 бит)
  3. VideoSeal 1.0 (256 бит)
  4. VideoSeal 0.0 (96 бит)

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.Hugging Face
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 VideoSeal 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 VideoSeal need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 VideoSeal support Russian?

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

Where can I download VideoSeal and what does it cost?

The VideoSeal 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 detectionAudioSealMeta · USACommercial use allowed

An imperceptible mark in synthetic speech plus a fast detector that finds it even inside a fragment of a long recording. The detector errs in both directions: a hit is a reason for a human to check, not proof.

DetailsDeepfake detectionWatermark Anything (WAM)Meta · USACommercial use allowed

An image watermark that can be applied to individual regions: the model shows which part of the image is marked. It errs in both directions - a human reviews the result.

DetailsDeepfake detectionTrustMarkAdobe Research and University of Surrey · USACommercial use allowed

An image watermark for arbitrary resolutions built for the Content Authenticity Initiative: it can both apply a mark and remove one. The detector errs in both directions - a human reviews the output.

Details

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