Open WebUI User Guides

Getting Started

This guide provides a step-by-step introduction to Open WebUI, covering initial setup, model selection, and image inference via chat. Learn how to access and sign up for Open WebUI, resolve account activation issues, select models, and perform image inference and generation using these models.

Allow Microphone Access

This guide helps you enable microphone access for Open WebUI, allowing voice recognition features like Speech-To-Text (STT) to work within the application. Due to security concerns, browsers block microphone access by default, but configuring your browser to treat the website as secure (https) can resolve this issue. Follow step-by-step instructions for popular browsers like Brave, Chrome/Chromium, Edge, and Opera, or use example instructions specific to Microsoft Edge.

Managing LLMs

This guide provides a step-by-step tutorial on managing Large Language Models (LLMs) for local instances of Open WebUI using Ollama, enabling users to find and add suitable models, understand model identifiers, and optimize performance based on size, type, and quantization method. By following these instructions, users can unlock the full potential of their Open WebUI experience and take advantage of various features and integrations with third-party applications.

Workspace Prompts: Automating Engaging Output

This guide demonstrates how to use workspace prompts to automate creative tasks, refine your prompts with LLMs, and streamline your workflow using Open WebUI’s Stable Diffusion Prompt Generator. You’ll learn how to import community-created prompts, invoke them in chat, and refine your results through multi-turn interactions, all while leveraging the power of AI-generated images.