kopperx/RelayVSR
Can I trust it?
Worth a closer look before you use it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active Check
Last change 42 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Official inference code for RelayVSR, a method for streaming 4x real-world video super-resolution that combines sparse Wan reference frames with a compact conditional decoder. Takes a video file or an ordered image directory and writes a 4x upscaled MP4 on an NVIDIA GPU.
Who it's for
Researchers and developers running video super-resolution on NVIDIA GPUs who want to reproduce or apply the RelayVSR method
How to use it
Install
uv sync --locked --extra cu128From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up kopperx/RelayVSR in my project. Follow its README: https://github.com/kopperx/RelayVSR. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Creative tools starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/kopperx/RelayVSR?ref=badge)Similar repos
- xiaoerofficial021-collab/FlowHMR-Windows
Windows desktop distribution of FlowHMR that reconstructs 3D human motion from video, with multi-person selection, a 3D preview, and multi-person FBX export. It also includes a Blender add-on for reta
- flowhmr/flowhmr
Official implementation of a generative flow-matching model that reconstructs 3D human motion from monocular video. It uses physics-based reward post-training (GRPO with a PHC+ controller) to produce
- KohakuBlueleaf/KohakUnlock
Research repository on unlocking tensor-compute throughput on NVIDIA GPUs via firmware-level changes. It documents a Linux initramfs port for one TU102 card and reproduction notes for Ampere, with C s
- xl03-bit/sm120-nvfp4-training
A PyTorch package for NVFP4 training on GeForce RTX 50-series and RTX PRO 6000 Blackwell (SM120) GPUs. It implements stochastic rounding and random Hadamard transforms in software, uses FP4 Tensor Cor
- Hyperstitioncc/Hyperkernel
Rust implementations of megakernels for NVIDIA B300 GPUs, with host servers for DeepSeek-V4.1-Flash LLM serving, openpilot driving-model inference, Evo 2 7B DNA generation and Matrix-Game 3.0 world-mo
- Shuyun-Wang/MatAnyone-E
Research code for MatAnyone-E, a video matting method that uses sparse memory propagation and a lightweight decoder to reduce the cost of high-resolution video matting. The README reports speed and me