---
title: SeedVR2_gguf_comfyUI
canonical_url: "https://www.modelscope.cn/models/svjack/SeedVR2_gguf_comfyUI"
md_url: "https://www.modelscope.cn/models/svjack/SeedVR2_gguf_comfyUI.md"
repository: svjack/SeedVR2_gguf_comfyUI
last_updated: 2025-10-11
license: apache-2.0
base_model:
  - ByteDance-Seed/SeedVR2-7B
  - ByteDance-Seed/SeedVR2-3B
base_model_relation: quantized
parameters: 24.7B
tensor_type:
  - F8_E4M3
  - F16
library_name:
  - gguf
  - safetensors
downloads: 2662
stars: 7
tags:
  - art
  - gguf
---

# SeedVR2_gguf_comfyUI

> SeedVR2_gguf_comfyUI - svjack 在 ModelScope 开源的模型。Place in ComfyUI/models/SEEDVR2 git clone https://github.com/numz/ComfyUI-SeedVR2VideoUpscaler -b nightly

svjack/SeedVR2_gguf_comfyUI 是 ModelScope 魔搭社区上的 24.7B 参数机器学习模型，采用 apache-2.0 许可，基于 ByteDance-Seed/SeedVR2-7B、ByteDance-Seed/SeedVR2-3B 构建。

- **Repository**: svjack/SeedVR2_gguf_comfyUI
- **License**: apache-2.0
- **Parameters**: 24.7B
- **Base model**: ByteDance-Seed/SeedVR2-7B, ByteDance-Seed/SeedVR2-3B
- **Tags**: art, gguf
- **Downloads**: 2662
- **Stars**: 7
- **Last updated**: 2025-10-11

Source: https://www.modelscope.cn/models/svjack/SeedVR2_gguf_comfyUI

---

### Place in ComfyUI/models/SEEDVR2
### git clone https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler -b nightly

# SeedVR2 Additional Upscale Models
This repository contains additional upscale models for SeedVR2 video upscaling, complementing the main [numz/SeedVR2_comfyUI](https://huggingface.co/numz/SeedVR2_comfyUI) repository.

## 📋 About SeedVR2
SeedVR2 is a high-quality video upscaling model that uses diffusion techniques to enhance video resolution while maintaining temporal consistency. This implementation is optimized for ComfyUI and supports both standalone and multi-GPU operation.

[![SeedVR2 Deep Dive Tutorial](https://img.youtube.com/vi/I0sl45GMqNg/maxresdefault.jpg)](https://youtu.be/I0sl45GMqNg)

## 🎯 GGUF Models
The GGUF format models in this repository are sourced from [cmeka/SeedVR2-GGUF](https://huggingface.co/cmeka/SeedVR2-GGUF), where additional GGUF versions and quantizations are available. We acknowledge and appreciate cmeka's work in converting these models to GGUF format.

## 📄 License
The code is released under the MIT License. Model weights are released under Apache 2.0 License.

## 🙏 Credits
- **Original SeedVR2**: [ByteDance-Seed/SeedVR](https://github.com/ByteDance-Seed/SeedVR) by ByteDance Seed
- **ComfyUI original integration**: [numz/ComfyUI-SeedVR2_VideoUpscaler](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler) by [numz](https://github.com/numz)
- **Further integration**: Additional code by [Adrien Toupet](https://github.com/adrientoupet) from [AInVFX](https://www.youtube.com/@AInVFX)
- **Official HuggingFace Models**: [numz/SeedVR2_comfyUI](https://huggingface.co/numz/SeedVR2_comfyUI)
- **GGUF conversions**: [cmeka/SeedVR2-GGUF](https://huggingface.co/cmeka/SeedVR2-GGUF) by [cmeka](https://huggingface.co/cmeka)
- **Tutorial**: [SeedVR2 Deep Dive](https://youtu.be/I0sl45GMqNg) by AInVFX

## 🛠️ Usage Guidelines
When using these additional models:
1. Compare output quality against official models
2. Monitor VRAM usage and performance
3. Test various input resolutions and batch sizes
4. Report issues on the [main repository](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/issues)
   
## 📞 Support
For questions and support:
- Use the [main repository issues](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/issues)
- Check the [comprehensive tutorial](https://youtu.be/I0sl45GMqNg) by AInVFX