> For the complete documentation index, see [llms.txt](https://sloyd.gitbook.io/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sloyd.gitbook.io/documentation/creating-3d/image-to-3d.md).

# 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.