SAVRN
Search Contact SAVRN

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

ModelPublisherParametersLicenseMonthly downloadsCheapest GPUs at 16-bit
SwiftVR H Oliday 5B apache-2.0 969 1x MI300X, $1.85/hr

Licenses

LicenseModelsCommercial use
apache-2.01Yes

Who Publishes Them

PublisherModels
H Oliday1

All 1 Models

Model · Video to video

SwiftVR

H Oliday

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…

Open weights apache-2.0 5B parameters diffusers

Questions

Which Video to video models are most downloaded?

By monthly downloads reported by the Hugging Face Hub: SwiftVR (969).

Other Tasks

See all