STStreamForce
StreamForce
Model Overview
StreamForce is a undisclosed-parameter model developed by Academic/Research. Released on 2026-06-01.
📊 Quick Specs
| Specification | Value |
|---|---|
| Parameters | undisclosed |
| Task | video-generation |
| Modality | image, video |
| License | Other/Custom |
| Type | research-preview |
✨ Key Features
- Physically Grounded Streaming Control: Accepts continuous time-varying force vectors to dynamically manipulate video streams
- Causal Autoregressive Architecture: Generates video sequentially from an initial image frame for low-latency interactive steerability
- Real-Time Speed (up to 16.6 FPS): Efficient force-controllable distillation pipeline enables streaming generation on a single GPU
- Unified Force Signal Representation: Combines local impulses and global environmental forces into a unified control signal space
- Physical & Photometric Realism: Maintains object persistence and motion plausibility under interactive user force interventions
🔗 Resources
- Hugging Face: StreamForce
- GitHub: Repository
- Paper: arXiv
- Website: Project Page
📜 License & Access
Other/Custom — See repository for specific license details.
Key Features
Physically Grounded Streaming Control: Accepts continuous time-varying force vectors to dynamically manipulate video streams
Causal Autoregressive Architecture: Generates video sequentially from an initial image frame for low-latency interactive steerability
Real-Time Speed (up to 16.6 FPS): Efficient force-controllable distillation pipeline enables streaming generation on a single GPU
Unified Force Signal Representation: Combines local impulses and global environmental forces into a unified control signal space
Physical & Photometric Realism: Maintains object persistence and motion plausibility under interactive user force interventions
You might also want to compare
Verified Sources
Tags
Model Specs
Parameters
Undisclosed
Context Window
undisclosed
License
Other/Custom
Deployment
Resources & Links
Curator Notes
Partially enriched via migration on 2026-07-25. Manual review recommended.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model