SwiftVR is a streaming one-step generative video restoration (VR) framework presented in SwiftVR: Real-Time One-Step Generative Video Restoration. - [2026/06] Release the inference code and pretrained weights LightX2V brings faster inference and lower GPU memory usage to SwiftVR (1.91× speedup and 65.71% lower peak GPU memory per request on a single H100). It also supports multi-GPU acceleration. Ready-to-use scripts cover image and video super-resolution, offline inference, and API serving. Get started with LightX2V → - Mask-free shifted-window self-attention (MFSWA). Each spatial window is pre-gathered into a dense tensor, so every attention call reduces to a single standard…
SAVRN Model Hub · Models by Task
Video to Video Models
1 open-weight video to video models in the SAVRN Model Hub, with H Oliday publishing the most.
1Models
1Publishers
5B to 5BParameter range
1Licenses
Most Downloaded
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| SwiftVR | H Oliday | 5B | apache-2.0 | 969 | 1x MI300X, $1.85/hr |
Licenses
| License | Models | Commercial use |
|---|---|---|
| apache-2.0 | 1 | Yes |
Who Publishes Them
| Publisher | Models |
|---|---|
| H Oliday | 1 |
All 1 Models
Questions
Which Video to video models are most downloaded?
By monthly downloads reported by the Hugging Face Hub: SwiftVR (969).