ComfyUI-RGT

★ 8

图像超分辨率Transformer模型ComfyUI节点模型推理

将 Recursive Generalization Transformer（RGT）集成到 ComfyUI，用于高质量图像超分辨率重建与便捷部署推理。

💡 在 ComfyUI 中对低分辨率图像进行超分辨率增强与细节恢复。

🍴 3 Forks💻 Python🔄 2024-06-20

🔗 GitHub 原文

📦

网盘下载

复制链接后前往夸克网盘下载

https://pan.quark.cn/s/b6135d9bd930

📄 README

ComfyUI-RGT

This repo cast Recursive Generalization Transformer for Image Super-Resolution to ComfyUI, the original paper link and github link

Usage

Install

cd comfyui/custom_nodes
git clone https://github.com/viperyl/ComfyUI-RGT.git
cd ComfyUI-RGT
pip install -r requirements.txt

model download from huggingface

# optional, make sure you have installed git lfs
# git lfs install
cd ComfyUI/models/
git clone https://huggingface.co/ViperYX/RGT

Example

an example workflow in workflow folder

Parameters

model_type: RGT and RGT-S model, former one usually better then the RGT-S
upsacle: x2, x3, x4 upscale
use_chop: process image with tiled operation, save lots vram