Image to 3D

Reconstruct a 3D model from one reference image or several views of the same object

Image to 3D grounds the generated model in a picture you already have. Connect a single reference image for a quick reconstruction, or two to four views of the same object to a Multi-View model for higher-fidelity geometry.

From a Single Image

1. Add a 3D Node and connect an image node (or upload a file) to its image input.

2. Pick a model with image input from the model picker.

3. Optionally add a prompt—some models use it to guide textures.

4. Click Run.

For best results, use an image of a single object on a plain background, shot from a slight three-quarter angle so both the front and one side are visible. Reference photos of full scenes or crowded compositions are often rejected by the provider or produce fused geometry.

From Multiple Views (Multi-View)

Connect two to four images of the same object (Rodin accepts up to five)—shot from different angles—into the node's image input, then select a Multi-View model from the picker (for example Tripo H3.1 Multi-View or Meshy 7.1 Multi-View).

Multi-view mode isn't selected automatically—connecting several images to a non-multi-view model just uses one of them. Pick the Multi-View variant of your chosen model from the picker yourself. Connect too few or too many images and the Run button tells you what's missing (e.g. "Connect at least 2 images").

• Order matters for models that expect ordered views (front, back, left, right)—connect images in that order

• Match lighting and framing across views so the model can align them

• A Sheet capture from another 3D Node produces eight consistent views you can reuse here

Models

Visit 3D Models for the full list of image-input models and which of them offer a Multi-View variant.