Generate an image from a text prompt

You don't always need a view, photo, or sketch to start rendering. When you have an idea but nothing on the board yet, you can generate an image from a written description alone.

When to use text-to-image

Text-to-image is useful when you want to:

• Explore an idea before you've built or streamed any geometry

• Generate quick reference or mood images at the earliest concept stage

• Produce entourage, textures, or context images to bring into other renders

If you already have a view, photo, or sketch to work from, start there instead → Generate an AI render from an image or view.

Generate an image from text

1. On the main Motif toolbar, select the icon for Image Generation

2. Type a description of the image you want to generate

3. Choose a AI Model, aspect ratio, resolution, and number of renderings — or leave them as the default

4. Press generate

💡 The default aspect ratio for Text to Image is 16:9. You can change this in the AI toolbar before generating if you need a different crop.

Because there's no input image, the prompt is doing all the work — so the more clearly you describe what you want, the better the result. For a full guide to prompt structure, camera cues, and examples, see → 📄 Prompting for AI generation

Next steps

• 📄 Edit rendered images

• 📄 Image Referencing

• 📄 AI Rendering tips, best practices, & known issues

Need help? Reach out to us at community.motif.io