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.
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.