# Image to 3D

### 🧠 What Is Image-to-3D?

Image-to-3D lets you upload a photo, sketch, or concept art and generate a detailed 3D model from it — no modeling skills required. It’s fast, experimental, and perfect for early prototyping, ideation, or creating high-detail background assets.

***

### 🚀 How It Works

1. **Upload an Image**\
   Use a clean, well-lit reference photo or concept sketch.
2. **Choose a Preset**\
   Select a style preset for your use case:
   * **High Quality** (\~40k tris, 1024x1024 tex): for rendering and concept art
   * **Low Poly** (\~5k tris, 512x512 tex): for games, VR, and web
   * **3D Printing** (no UVs, optimized mesh): for printable models
3. **Generate Model**\
   Sloyd's AI creates a 3D model from your image with baked textures and geometry based on real-world scale and proportions.
4. **Texture & Export**
   * The image decides what type of texture the model will get. Try different images for different styles. 
   * Export as `.glb`, `.stl`, `.obj`, `.ply`, `.fbx`, `.blend`, or `.stl` 

{% hint style="warning" %}
Only .glb, .usdz, and .blend stores textures in the object.
{% endhint %}

***

### ✅ Best Use Cases

* Creating 3D miniatures from photos
* Testing early concepts
* Filling game environments with organic background props
* Quickly visualizing ideas before manual modeling

***

### 🔍 Tips for Best Results

* ✔ Use high-resolution, evenly-lit images
* ✔ Include the full object in-frame
* ✔ Avoid cluttered backgrounds and shadows
* ✔ Choose simple, solid shapes
* ❌ Avoid reflective or transparent surfaces
* ❌ Avoid cropped or partial views of objects

> 🧪 *Pro Tip:* Slightly angled images work best. 

***

### ⚠️Limitations to Be Aware Of

* Reflective or transparent materials (glass, chrome)
* Very thin details (wires, chains)
* Facial features and characters may look rough or “off”
* Generated geometry is **not parametric** — models can’t be edited with sliders like in the Template Editor
* Complex or multi-object scenes produce inaccurate results
* Complex geometry may need cleanup if used in games.
* Snapshots, palettes, and toon shaders are **only available in Template Editor**

***

### 📦Export Formats

Supported export formats:

* `.glb`, `.obj`, `.ply`, `.stl`

Use `.stl` for 3D printing, `.glb` for games and WebGL, `.obj` for broad compatibility.

***

### 🔁 Combine Workflows

Use Image-to-3D alongside other Sloyd tools:

* **Text to 3D**: best for fast ideation without references
* **Multi-Image to 3D:** best when you have multiple views of the same object
* **Text to Image:** best for fast concepting and reference generation
* **Template Editor**: best for clean, editable, game-ready assets

***

### 🌍 Who’s It For?

* **Game Developers**: Use AI-generated assets as decoration or background fillers.
* **3D Printing Hobbyists**: Create print-ready models with the 3D Printing preset.
* **Concept Artists**: Turn 2D designs into visualized 3D forms quickly.
* **Students/Educators**: Teach modeling concepts without Blender or Maya.

***

### 🧪 Status

{% hint style="warning" %}
Image-to-3D is under active development. Quality will continue to improve over time, and feedback helps guide what to prioritize next.
{% endhint %}

***

### 🔗 Try It Now

Head to [app.sloyd.ai](https://app.sloyd.ai/) → Choose **Image to 3D** in the **Create** section.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://sloyd.gitbook.io/documentation/creating-3d/image-to-3d.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.