FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Paper
•
2510.12747
•
Published
•
37
JunhaoZhuang
JunhaoZhuang
AI & ML interests
None yet
Recent Activity
reacted
to
their
post
with 🚀
21 days ago
✨ **FlashVSR v1.1 Released**
We have released **FlashVSR v1.1**, an improved version of our framework **towards real-time diffusion-based video super-resolution**.
This update focuses on enhancing **temporal stability**, **fidelity**, and **robustness** in long-video and streaming scenarios.
Compared with v1, the new version provides smoother temporal consistency, better detail preservation, and more stable performance across different resolutions.
**FlashVSR v1.1** also includes updated model weights and streamlined inference scripts ⚙️, making it easier to integrate and reproduce.
You can explore the update here:
* [🚀 FlashVSR v1.1 on Hugging Face](https://huggingface.co/JunhaoZhuang/FlashVSR-v1.1)
* [📄 Paper (arXiv:2510.12747)](https://arxiv.org/abs/2510.12747)
* [🌐 Github](https://github.com/OpenImagingLab/FlashVSR)
posted
an
update
21 days ago
✨ **FlashVSR v1.1 Released**
We have released **FlashVSR v1.1**, an improved version of our framework **towards real-time diffusion-based video super-resolution**.
This update focuses on enhancing **temporal stability**, **fidelity**, and **robustness** in long-video and streaming scenarios.
Compared with v1, the new version provides smoother temporal consistency, better detail preservation, and more stable performance across different resolutions.
**FlashVSR v1.1** also includes updated model weights and streamlined inference scripts ⚙️, making it easier to integrate and reproduce.
You can explore the update here:
* [🚀 FlashVSR v1.1 on Hugging Face](https://huggingface.co/JunhaoZhuang/FlashVSR-v1.1)
* [📄 Paper (arXiv:2510.12747)](https://arxiv.org/abs/2510.12747)
* [🌐 Github](https://github.com/OpenImagingLab/FlashVSR)
updated
a model
21 days ago
JunhaoZhuang/FlashVSR-v1.1
Organizations
authored
a
paper
about 1 month ago
authored
a
paper
5 months ago
authored
2
papers
7 months ago
authored
4
papers
11 months ago
A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
Paper
•
2312.03594
•
Published
•
2
Image Inpainting Models are Effective Tools for Instruction-guided Image Editing
Paper
•
2407.13139
•
Published
•
1
TextureDiffusion: Target Prompt Disentangled Editing for Various Texture Transfer
Paper
•
2409.09610
•
Published
ColorFlow: Retrieval-Augmented Image Sequence Colorization
Paper
•
2412.11815
•
Published
•
26