Skip to main content

​
ComfyUI SeedVR2 Introduction

SeedVR2 (arXiv:2506.05301, from ByteDance Seed) is a one-step diffusion-based video restoration model. It performs adversarial training against real data to restore and upscale images and videos with high fidelity. SeedVR2 is natively supported in ComfyUI (PR #14424). Key capabilities:
  • Conservative upscaling: preserves original structure and detail while enhancing clarity
  • One-step inference: single forward pass for both image and video upscaling
  • Multiple model sizes: 3B and 7B variants with FP16, FP8, INT8, NVFP4, and MXFP8 quantizations
  • Both image and video: supports single-image upscaling and video resolution enhancement
SeedVR2 comes in two sizes. The 3B model is a smaller variant with lower VRAM requirements, suitable for users with limited hardware. The 7B model is a larger variant that delivers higher quality results at the cost of increased VRAM and processing time. Both are available under the Apache 2.0 license.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Model Installation

Download the SeedVR2 checkpoint(s) from the Comfy-Org SeedVR2 repository and save them to the corresponding ComfyUI folder: Place the files in the following directories:

​
Example Workflows

​
1. Image Upscale (3B INT8)

What it does: Upscales a single image using the SeedVR2 3B INT8 model. The INT8 quantized variant offers a good balance of quality and reduced VRAM usage.

Download Workflow

Download JSON or search “SeedVR2 3B Int8: Upscale Image” in Template Library

Download Sample Image

Get the example input image for this workflow
SeedVR2 3B INT8 upscale preview

​
1.1 Steps to Run

  1. Place your image in the ComfyUI/input/ folder and select it in the Load Image node
  2. Select the seedvr2_3b_int8_convrot.safetensors checkpoint in the SeedVR2 model loader
  3. Click Queue or use Ctrl(cmd) + Enter to run

​
2. Image Upscale (7B INT8)

What it does: Upscales a single image using the SeedVR2 7B INT8 model. The larger 7B model delivers higher quality results with INT8 quantization for efficient VRAM usage.

Download Workflow

Download JSON or search “SeedVR2 7B Int8: Upscale Image” in Template Library

Download Sample Image

Get the example input image for this workflow
SeedVR2 7B INT8 upscale preview

​
2.1 Steps to Run

  1. Place your image in the ComfyUI/input/ folder and select it in the Load Image node
  2. Select the seedvr2_7b_int8_convrot.safetensors checkpoint in the SeedVR2 model loader
  3. Click Queue or use Ctrl(cmd) + Enter to run

​
3. Video Upscale (3B INT8)

What it does: Upscales a video using the SeedVR2 3B INT8 model. The workflow enhances resolution while maintaining temporal consistency across frames. Ideal for restoring old or degraded footage and upscaling low-resolution videos.

Download Workflow

Download JSON or search “SeedVR2 3B Int8: Upscale Video” in Template Library

Download Sample Video

Get the example input video for this workflow

​
3.1 Steps to Run

  1. Place your video in the ComfyUI/input/ folder and select it in the Load Video node
  2. Select the seedvr2_3b_int8_convrot.safetensors checkpoint in the SeedVR2 model loader
  3. Click Queue or use Ctrl(cmd) + Enter to run

​
Performance

Higher target resolutions require more processing time. The INT8 variant provides efficient inference with reduced VRAM usage compared to FP16.

​
Community Resources