Overview:

onnx-web is a tool designed to simplify the process of running Stable Diffusion and other ONNX models, allowing users to focus on creating high-quality art. It provides hardware acceleration support for both AMD and Nvidia GPUs, along with a reliable CPU software fallback. The platform is user-friendly, accessible on various devices, and offers a range of features for image processing and artistic expression.

Features:

• Support for SDXL and SDXL Turbo
• Wide variety of schedulers: DDIM, DEIS, DPM SDE, Euler Ancestral, LCM, UniPC, and more
• Hardware acceleration on AMD and Nvidia GPUs
• Tested on CUDA, DirectML, and ROCm
• Half-precision support for low-memory GPUs
• Software fallback for CPU-only systems
• Web app for image generation and viewing
• Multiple language translations available
• Support for various diffuser pipelines and image manipulation techniques

Installation:

To install onnx-web, follow these steps:

1. Clone the repository from Github:

   git clone https://github.com/onnx-web.git
   

2. Install dependencies using npm:

   npm install
   

3. Start the application:

   npm start
   

4. Access the onnx-web interface on your browser at http://localhost:3000.

Summary:

onnx-web is a versatile tool that empowers users to engage in generative art and image manipulation effortlessly. With support for various models, accelerators, and a user-friendly interface accessible across devices, it provides a seamless experience for artists and creators to explore and enhance their creative endeavors. Its features, including hardware acceleration support, scheduler variety, and translation options, make it a comprehensive platform for image processing and artistic expression.