How to Use Multimodal Input in Trae

Historical tutorial / news archive. The original instructions and claims describe the 2025 version, not the current product.

Multimodal input allows you to add images during chats with the AI assistant, enabling more accurate and efficient communication of your needs through visual context.

Overview

You can add various types of images to enhance your chat interactions, including:

• Error screenshots
• Design drafts
• Reference styles
• And more

How to Add Images

Both Builder and Chat modes support adding images through multiple methods:

1. Drag and drop images from:

   • External sources into the chat input box
   • Current project file tree into the chat input box

2. Paste images directly:

   • Copy an image to your clipboard
   • Paste (Cmd/Ctrl + V) into the input box

3. Use the image selector:

   • Click the Images button at the bottom left of input box
   • Select images from your local computer

Example Use Cases

Debugging with Error Screenshots

When encountering errors, you can:

1. Take a screenshot of the error message
2. Add it to the chat
3. Let the AI assistant analyze the error and provide solutions

Code Generation from Designs

To implement designs efficiently:

1. Upload your design draft or mockup
2. Ask the AI assistant to generate the corresponding code
3. Review and refine the generated code with the assistant’s help

The AI assistant will analyze the visual content and provide relevant assistance based on your needs.

Related TRAE guides

• TRAE product overview
• Trae IDE / TraeCode Download
• TraeCode Guide
• TraeWork Guide
• TRAE Pricing: TraeCode & TraeWork
• TRAE Models & Model Access
• TraeWork vs TraeCode (Trae IDE)
• Trae MCP Setup & Troubleshooting