You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

40 lines
1.8 KiB
Markdown

---
title: Guide to Using Text-to-Image Models in LobeChat
description: >-
Learn how to utilize text-to-image generation in LobeChat using DALL-E and
Midjourney plugins. Generate images seamlessly with AI assistance.
tags:
- Text-to-Image Models
- LobeChat
- DALL-E
- Midjourney
- Plugin Installation
- AI Assistance
---
# Guide to Using Text-to-Image Models in LobeChat
LobeChat supports text-to-image generation through a plugin mechanism. Currently, LobeChat comes with the built-in DALL-E plugin, which allows users to generate images using OpenAI's DALL-E model. Additionally, users can also install the official Midjourney plugin to utilize the Midjourney text-to-image feature.
## DALL-E Model
If you have configured the OpenAI API, you can enable the DALL-E plugin directly in the assistant interface and input prompts in the conversation for AI to generate images for you.
<Image alt={'DALL-E Plugin'} src={'https://github.com/user-attachments/assets/7b11b795-4dd3-4020-a9ba-a3723d5f1f28'} />
If the DALL-E plugin is not available, please check if the OpenAI API key has been correctly configured.
## Midjourney Model
LobeChat also offers the Midjourney plugin, which generates images by calling the Midjourney API. Please install the Midjourney plugin in the plugin store beforehand.
<Image alt={'Midjourney Plugin'} src={'https://github.com/user-attachments/assets/5f526846-02cd-4dbc-b6e3-a603fa5ac8e7'} />
<Callout type={'info'}>
info For plugin installation, please refer to [Plugin Usage](/docs/usage/plugins/basic-usage)
</Callout>
When using the Midjourney plugin for the first time, you will need to fill in your Midjourney API key in the plugin settings.
<Image alt={'Midjourney Plugin Settings'} src={'https://github.com/user-attachments/assets/a5d7a543-aec5-457e-a36c-aa1f82f7bc8a'} />