Downloads · 30 days
0
videoseal-1.0
Svetozar1993/videoseal-1.0
videoseal-1.0 is a other model from Svetozar1993. Use it for the other task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
Neural network-based invisible video watermarking model from Meta's VideoSeal.
Access
Public
Updated Feb 25, 2026
Repo size
228 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth228 MB · 100%
At a glance
- Task
- other
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026
- SHA
- c9c70886
Model card
From the Hugging Face model README
VideoSeal 1.0
Neural network-based invisible video watermarking model from Meta's VideoSeal.
Model Details
- Architecture: UNet embedder (Y-channel) + ConvNeXt Tiny detector
- Message length: 256 bits
- Processing resolution: 256x256
- Blending: Additive (default strength: 0.2)
- Attenuation: JND (Just Noticeable Difference)
Usage
pip install videoseal torch torchvision ffmpeg-python tqdm
# Embed watermark (auto-generates unique 256-bit message)
python video_watermark.py embed -i input.mp4 -o watermarked.mp4
# Extract watermark
python video_watermark.py extract -i watermarked.mp4
# Verify against registry
python video_watermark.py verify -i suspect.mp4
Robustness
| Scenario | Bit Accuracy |
|---|---|
| Direct extraction | ~100% |
| Re-encoded at CRF 30 | ~98% |
| Resolution scaling | Strong |
| Multiple re-encodes | Strong |
Files
y_256b_img.pth— PyTorch checkpoint (~228MB)
Source
- Task
- other
- Library
- pytorch
- License
- mit
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026