# numz/ComfyUI-SeedVR2_VideoUpscaler

Official SeedVR2 Video Upscaler for ComfyUI

Repository: https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler
Canonical: https://ross.abutalabs.com/products/comfyui-seedvr2_videoupscaler
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, comfyui, comfyui-nodes, upscaler, video-processing
Last push: 2025-12-24T08:52:32+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 58, release rhythm 62, longevity 31
- inputs: {"age_days": 439, "days_push": 252, "days_rel": 253, "gap_med": 1, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2786, forks 226 (observed 2026-08-28T04:07:21.852496+00:00)

## What it is
The official ComfyUI integration of ByteDance's SeedVR2 model for high-quality video and image upscaling, provided as custom nodes. It can also run as a standalone multi-GPU CLI outside ComfyUI.

## Use cases
- upscale low-resolution videos with AI
- enhance video quality in ComfyUI workflows
- upscale images with SeedVR2
- run video upscaling across multiple GPUs
- restore old or blurry footage
- batch upscale videos from the command line

## When to choose
- you already use ComfyUI and want AI video upscaling in your workflows
- you need high-quality one-step diffusion-based video restoration
- you want to leverage multiple GPUs for upscaling jobs

## When to avoid
- you need a lightweight real-time upscaler without GPU requirements
- you don't use ComfyUI and prefer a GUI application
- you have limited VRAM and cannot run large diffusion models

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, image-processing, machine-learning, cli
- domain: image-processing, machine-learning, media
- platform: python, cross-platform, cli
- tags: comfyui, comfyui-nodes, upscaler, seedvr2, video-upscaling, super-resolution, multi-gpu, video, gpu

## Member repositories
- numz/ComfyUI-SeedVR2_VideoUpscaler (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:21.852496+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:01.693244+00:00, confidence not recorded.
  - readme: https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler (fetched 2026-08-28T04:07:21.852496+00:00, sha 53608b4302b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.