Image to 3D Model with AI Photo to model, free

Add a photo of a chair, a lamp or a part, say how big it is, and the AI rebuilds it from simple shapes and proportions. The photo is a reference: the AI models what it sees, checks six views of its result against the picture and lets you correct it by chat.

Free. Use your own Anthropic or OpenAI key.

Also from Innerscene: Circadian Lab, a free lighting calculator for room illuminance, melanopic EML, and glare.

Watch how it works

How it works

  1. 1. Describe it or add a photoType what you want in plain words, with sizes if you know them, or add a photo as a reference. Describe an object or a person.
  2. 2. The AI builds and checks itThe AI writes an OpenSCAD program for an object, or sets up the character generator for a person. It looks at six rendered views of the result and fixes what is wrong, up to five builds per message.
  3. 3. Refine and exportThe model opens in the viewer at real size. Ask for changes in the chat, move the sliders, then download it or pick a format from the Export menu.

Why make it with AI here

  • A catalogue photo of a chair becomes a sized model you can place in a scene or drawing.
  • Adding one real dimension, like "seat height 450 mm", makes the whole model scale correctly.
  • The result is clean geometry with editable sliders, which a scan cannot give you.

Prompts to try

Click one to open it in the AI panel, then change the sizes to suit.

Exporting your photo-based model

  1. Add the photo in the AI panel and type a short description with one or two real sizes.
  2. Correct the result by chat until it matches the photo closely enough.
  3. Export GLB for web and AR, STL for printing, or OBJ for most 3D programs.

The model is rebuilt from shapes, so the photo's textures and fine details are not copied. Colours are set to match the photo by eye.

Best export formats: GLB, STL, OBJ

Good to know

It is not photogrammetry, so it will not capture an exact replica, surface texture or a branded product's exact design. Animals, faces and sculpted shapes come out rough.

Cost and privacy

You use your own Anthropic or OpenAI API key. It is stored only in your browser and sent only to that provider, which bills you directly: a model typically costs $0.05 to $0.30 at Standard quality and up to about $1 at Detailed, and Innerscene charges nothing. Your key and prompts are not sent to Innerscene; we record anonymous usage statistics such as the steps used, the model chosen, token counts, a cost estimate and whether a model was made.

How to get an Anthropic or OpenAI API key

Read the full guide: API keys, refining and exporting

Questions

▶Can AI turn a picture into a 3D model?
Yes. Add a photo in the AI panel, and the AI rebuilds the object from simple shapes and proportions. It works best on furniture, lighting, products and simple parts.
▶Is this the same as 3D scanning?
No. A scan measures the real surface; here the AI interprets the photo and models it, so give it a real dimension for accurate size.
▶Can I make a 3D model of a person from a photo?
The AI can use a photo to choose settings for the built-in character generator, such as build, hair and clothes. It does not reproduce a person's face.
▶What photos work best?
A clear, well-lit photo of a single object from a three-quarter angle, with a plain background. A second photo from the side helps.

What it can make

Floor plans and layouts

Molecules, proteins and crystals

Make a model for any format

Make a model for your app

More ways to use it

AI Generator