# How Kaedim Works

Kaedim's approach to generating 3D models combines our state-of-the-art machine learning algorithms with our in-house art team.  Our in-house team of artists help refine our 2D to 3D reconstruction outputs and improve future AI-generated models. This guarantees users get a production-ready 3D model, every time.

Today, our process provides a 10x speedup compared to traditional art outsourcing. But we're not stopping there - each month, we implement multiple improvements to our machine-learning models with the goal of automating a greater portion of the pipeline while maintaining our high-quality standards, leading to faster outputs for you and your team.

## Inputs

<figure><img src="/files/rJnTDOwk6WZ539oYnkW3" alt="" width="188"><figcaption></figcaption></figure>

You can input up to 10 images to generate your model. Before making your first submission, please check our [input guidelines](/creating-assets/input-guidelines.md) to ensure that you receive the best possible results.

{% content-ref url="/pages/nCusskRblfOh93dRw7to" %}
[Input Guidelines](/creating-assets/input-guidelines.md)
{% endcontent-ref %}

## Automated Generation

<figure><img src="/files/SMbo2AwpqZWs4Qosa8dw" alt="" width="188"><figcaption></figcaption></figure>

Once you've submitted your images, they'll go through a series of preprocessing steps to help our AI accurately represent them in 3D. The processed images then enter our 2D to 3D reconstruction step of the pipeline and exit as a 3D model.&#x20;

## Artist Refinement

<figure><img src="/files/mhclMGmSrAFaxKRKsOG6" alt="" width="188"><figcaption></figcaption></figure>

Though our 3D reconstruction technology has made large strides in producing quality models, the output isn't always perfect. Our art team verifies and cleans all outputs, making any necessary edits to ensure that you always receive a production-ready model

This guarantees a great experience for our users since our outputs are of the highest quality, and it also helps improve our machine-learning models. We're gathering generations and their adjusted versions in real time, creating a feedback loop for our AI to improve itself.

## Model Download

<figure><img src="/files/58AAyR2HDJ4ORJf8HhXI" alt="" width="188"><figcaption></figcaption></figure>

Your model is now ready to export. Currently, we provide OBJ, OBJ (Pre-modifiers), FBX, MTL, USD, GLB, and GLTF formats.

{% content-ref url="/pages/PmVBBMF3SQTp9VvHyiSk" %}
[Download](/managing-assets/exporting-assets/download.md)
{% endcontent-ref %}

## A Note on Fully Autonomous Generations

<figure><img src="/files/gitFRdfSHFqotbOh4vGl" alt="" width="375"><figcaption></figcaption></figure>

The above process is fast, but it still takes some in-house work. The Kaedim team is working towards achieving better and better 3D reconstructions, automating more and more object categories. This work is aiming towards making our software accessible to more prosumers and indie projects.&#x20;

We're improving our system every day and aim for a fully autonomous release in the future. Currently, we're primarily focusing on enterprise customers that have a significant need for Kaedim's large-scale production capabilities.&#x20;


---

# 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://docs.kaedim3d.com/welcome/how-kaedim-works.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.