#182 · Primary category: Video & Animation
ComfyUI-SeedVR2_VideoUpscaler
Official SeedVR2 Video Upscaler for ComfyUI
Project last updated:12/24/25
GitHub Stars
2.8K
Forks
228
Contributors
12
License
Apache-2.0
Why we included this project
People restoring old footage or trying to make gameplay captures look decent on modern displays will appreciate having ByteDance's SeedVR2 one-step diffusion upscaler available as a ComfyUI node. You can drop it straight into an existing node graph, or skip ComfyUI entirely and run the bundled multi-GPU standalone CLI to batch upscale whole clips on a dedicated box. It handles both video and still images, and the maintainers have paid attention to the messy details: memory usage across CUDA, ROCm, and Apple Silicon, plus GGUF-quantized VAEs for cards with limited VRAM. The changelog shows fixes for ffmpeg hangs, 10-bit encoding, and backend fallbacks, which is exactly the kind of reliability you want when processing long sequences. If your team wants a reproducible upscaling step that.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
yt-dlp
A feature-rich command-line audio/video downloader
MoneyPrinterTurbo
Generate HD short videos from a topic or keyword with an automated AI workflow.
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image
manim
Animation engine for explanatory math videos
anime
JavaScript animation engine