Meta
Video Seal
What Meta says Video Seal puts into the files it makes, by file type, quoted from Meta's own pages. Covers Meta's open-source Video Seal watermarking model, released for others to integrate; it is not a record of Meta AI output.
At a glance
| File type | Content Credentials | Invisible watermark | AI label in metadata | Visible mark | Tool named in metadata |
|---|---|---|---|---|---|
| Video | Not stated | Open-source model | Not stated | Not stated | Not stated |
Video
- Content CredentialsA signed record (C2PA) of how the file was made, sealed so any change shows.
Not stated. None of Meta's pages listed under Sources read says so.
- Invisible watermarkA signal woven into the pixels, frames, audio or wording, meant to survive copying.
On December 12, 2024 Meta released Video Seal, an open-source invisible video watermarking model with an optional hidden message, which it said is resilient to blurring, cropping and common compression, for others to integrate. Its repository says the models and code are released under the MIT license, with version 1.0 released in March 2025.
Meta does not say it applies Video Seal to Meta AI output.
Sharing new research, models, and datasets from Meta FAIR
Quoted passage Meta Video Seal
Today, we’re releasing Meta Video Seal, a state-of-the art comprehensive framework for neural video watermarking. Video Seal adds a watermark (with an optional hidden message) into videos that is imperceptible to the naked eye and can later be uncovered to determine a video’s origin. The watermark has proven resilience against common video editing efforts like blurring or cropping, as well as compression algorithms commonly used when sharing content online. We’re publicly releasing the Video Seal model under a permissive license, along with a research paper, training code, and inference code." "Watermark Anything, Video Seal, and Audio Seal—our previous work on post-hoc audio watermarking—are now all available for download and ready to be integrated.
Quoted passage Highlights; Latest Updates
Open Source: All models, training code, and evaluation tools released under MIT license" "March 2025: VideoSeal v1.0 with improved 256-bit model and enhanced robustness" "December 2024: Initial VideoSeal release with 96-bit baseline model
- AI label in metadataA plain metadata field (IPTC Digital Source Type) saying AI made the content. Anyone can add or remove it.
Not stated. None of Meta's pages listed under Sources read says so.
- Visible markA mark you can see, such as a logo or a sparkle in a corner.
Not stated. None of Meta's pages listed under Sources read says so.
- Tool named in metadataThe tool or model written into ordinary file fields, such as Software or Creator.
Not stated. None of Meta's pages listed under Sources read says so.
Limits and detection
- Checking tool from the makerA way the maker offers to check a file for its traces.
Meta releases Video Seal's models and code under the MIT license, for others to integrate.
Meta describes no hosted checking tool for Video Seal on the pages read.
Sharing new research, models, and datasets from Meta FAIR
Quoted passage Meta Video Seal
Today, we’re releasing Meta Video Seal, a state-of-the art comprehensive framework for neural video watermarking. Video Seal adds a watermark (with an optional hidden message) into videos that is imperceptible to the naked eye and can later be uncovered to determine a video’s origin. The watermark has proven resilience against common video editing efforts like blurring or cropping, as well as compression algorithms commonly used when sharing content online. We’re publicly releasing the Video Seal model under a permissive license, along with a research paper, training code, and inference code." "Watermark Anything, Video Seal, and Audio Seal—our previous work on post-hoc audio watermarking—are now all available for download and ready to be integrated.
Quoted passage Highlights; Latest Updates
Open Source: All models, training code, and evaluation tools released under MIT license" "March 2025: VideoSeal v1.0 with improved 256-bit model and enhanced robustness" "December 2024: Initial VideoSeal release with 96-bit baseline model
Sources read
Each page below was read and the quoted passage found on it. Last verified October 19, 2026.
- Labeling AI-Generated Images on Facebook, Instagram and ThreadsMeta (Newsroom)
- What’s New Across Our AI ExperiencesMeta (Newsroom)
- Introducing Muse Image and Muse VideoMeta (AI at Meta blog, Meta Superintelligence Labs)
- Generate images, edit photos, restyle rooms, and more for free with Meta AIMeta (AI at Meta)
- AI IdentificationMeta (meta.ai)
- Sharing new research, models, and datasets from Meta FAIRMeta (AI at Meta blog)
- Content Seal READMEMeta (facebookresearch on GitHub)
- VideoSeal READMEMeta (facebookresearch on GitHub)
- AudioSeal READMEMeta (facebookresearch on GitHub)
- Movie Gen: A Cast of Media Foundation Models (research paper)Meta (AI at Meta research)
- Meta Joins the C2PA Steering CommitteeC2PA