Unity AI Open Beta: Create props with the 3D Object Generator
The Unity AI Open Beta is here. In today’s article, we’re covering how to generate 3D meshes from text prompts and reference images – directly inside the Unity Editor.
Creating 3D assets for prototyping can be a time-consuming and costly process. Reference art takes time to find, model, and optimize – and by the time it exists, the design has often already changed.
The Unity AI 3D Object Generator removes that step. Describe what you need, optionally drop in a reference image, and the generator returns a placeholder asset in seconds.
What the 3D Object Generator produces
The 3D Object Generator creates static 3D mesh prefabs. It’s well-suited for simple, single-part props: household items, environment details, decorative objects, and any asset that needs to exist in three dimensions but doesn't need to move independently. The output is a standard Unity prefab containing a mesh and materials, and it drops into any Scene the same way as any other asset.
Two ways to generate a 3D object
You can generate a 3D object directly from the Generators window – for more control over inputs and model selection – or through the AI Assistant using natural language.
Using the Generators window
1. Open the 3D Object Generator. In the Unity Editor, select AI > Generate New > 3D Object. A new mesh file is created in the Assets folder.
2 .Open the generator. Double-click the new file to open the 3D Object Generator window.
3. (Optional) Select a model. Select Change to choose your preferred AI model.
4. Provide a reference image. You can:
i. Select an existing image from your project
ii. Import an image from disk
iii. Generate one using another Generator (for example, using the Sprite or Texture Generator)
5. Drag the reference image to the Image Reference field.
6. Select Generate.
Using the Unity AI Assistant
The Unity AI Assistant can generate 3D objects from a natural-language prompt alone. For example: “Create a 3D model of a cereal box.”
If you don't provide an image, the Assistant first generates a reference image and then uses it to produce the 3D object. If you include an image in the conversation, the Assistant uses it directly – handling any required preprocessing, such as background removal, before generating.
Reference images and output quality
For higher visual quality and more predictable results, use a reference image rather than text alone. A clear, isolated subject on a plain or transparent background tends to produce the best output.
Managing generated assets
All assets produced by Unity AI Generators carry embedded metadata flagging them as AI-generated. This makes them easy to identify in the Project window and ensures you can track them for app store declarations. Generated 3D objects used for prototyping can be replaced with final art at any point without disrupting your scene layout – the prefab reference stays in place.
Generators can be disabled entirely in the Unity Dashboard.
More on Unity AI
If you’re interested in reading more about what’s available in the Unity AI Open Beta, we invite you to read other articles in this ongoing series:
Try Unity AI today
Unity AI open beta is available now for all Unity 6 developers. Sign up for a free trial, explore the Unity AI Assistant, connect your preferred tools via the Unity AI Gateway, and start experimenting with what your development workflow looks like with a project-aware AI agent built in.
Sign up and learn more about plans, pricing, and data privacy at unity.com/features/ai
Full documentation is available in the Unity AI docs linked from the Editor or at docs.unity3d.com.
Unity AI Assistant is currently in open beta. As such, features, behavior, and availability described in this post are under active development and may change, be limited, or be discontinued without notice.