Transform your photos and images into immersive 3D worlds with Marble’s image-to-world generation. Learn how to select the best images and optimize your prompts for stunning results.
Image prompting in Marble works by analyzing your uploaded image and generating a 3D environment based on its content, style, and composition. The AI understands spatial relationships, lighting, and architectural elements to create explorable worlds.
You can do so dragging in images to the omnibox; it will expand with 2D input mode, which allows you to start a generation by clicking on Create.
For image file specifications, see Prompt Guidelines →
Close-up Shots: Extreme close-ups of objects without spatial context
Characters: Human and animals are not well supported by the model yet.
Blurry Images: Blurry images result in ambiguous 3D interpretations.
Abstract Images: Pure abstractions without recognizable spatial elements
Flat Graphics: Logos, text, or 2D graphics without depth
Poor Lighting: Very dark, overexposed, or unclear images
Images with Border: Crop your image carefully to avoid flat patches of image border showing up in the 3D world.
Remember that Marble’s AI interprets your image creatively, so the generated world may expand beyond what’s visible in your original image, creating a fuller, explorable environment.