- VISUALS
- REFINEMENT
- ASSETS
- HUMAN
Short answer
How can I make images with my AI?
You provide a text description in your chat, and your agent uses the DeepAI connector to render the image. You'll get visual assets directly in your conversation window.
The results you get
Visual outcomes
Your agent produces different types of visual outputs based on your prompts.
VISUALS
Custom rendered images
The AI uses your text to create a unique image. You get a specific file that matches your description.
REFINEMENT
Iterative adjustments
If the image isn't right, you tell the agent what to change. It re-runs the process to fix details.
ASSETS
Ready-to-use files
The generated images are ready for your projects. You can download them directly from your chat history.
HUMAN
Creative direction
You stay in control of the vision. The AI handles the rendering, but you decide the style and subject.
The workflow
What your AI does when you ask for an image.
The process moves from your words to a finished visual asset.
Interpret prompt
Your agent reads your description and extracts the key visual elements like style, lighting, and subject.
generate_imageExecute render
The agent sends the refined description to the DeepAI engine to start the generation process.
generate_imageDeliver asset
Once the image is ready, the agent brings the visual back into your chat window.
generate_imageApply feedback
If you want a different color or angle, the agent updates the parameters and tries again.
generate_image
Try it
Copy these to start.
Paste these into your chat to see how it works.
Starting points
These are basic ideas. Swap out the subjects and styles to get exactly what you want.
DeepAI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_hbTBqGz3hnek9jnQSt4T2NDWqCNDJ14KfUd5xz5E/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — DeepAI capabilities are ready to use.
{
"mcpServers": {
"deepai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_hbTBqGz3hnek9jnQSt4T2NDWqCNDJ14KfUd5xz5E/mcp"
}
}
}Generate an image of a futuristic cyberpunk city with neon lights and heavy rain.
Create a high-quality oil painting of a golden retriever sitting in a field of sunflowers.
Make a minimalist vector logo for a coffee shop named 'Midnight Brew'.
Render a 3D isometric view of a cozy mountain cabin during a snowstorm.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect DeepAI once, then ask.
Click the link to connect. Your credentials stay encrypted, and you can start generating images immediately in your preferred client.
Connect DeepAI to your AIFAQ
How this task behaves
- 01
Can the AI edit an existing photo I upload?
No. This connector is specifically for generating new images from text descriptions.
- 02
Does the AI decide the art style?
You do. While the AI interprets your words, the style is determined by the descriptions you provide.
- 03
Can I generate videos?
No. The current capability is limited to static image generation.
- 04
Who owns the generated images?
Ownership depends on the terms of the service you are using, but the AI simply acts as the tool to create them.
- 05
Can the AI browse the web to find reference images?
No. It generates images from scratch based on your text, it doesn't search for existing files online.
More questions about DeepAI? The Connector page answers them. See everything the DeepAI Connector can do
Connect DeepAI to Claude, Cursor, ChatGPT & more
