> For the complete documentation index, see [llms.txt](https://guide.404.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.404.xyz/404-gen-user-guide/getting-started/404-gen-prompt-guide.md).

# 404—GEN Prompt Guide

A prompt is a short text phrase or an image that **404—GEN** interprets to generate a 3D Model. This guide covers how to craft effective prompts and refine your inputs for the highest-quality 3D assets.

### Text Prompts

When writing text prompts, the golden rule is to describe a single 3D object that can be observed from multiple angles.

* **Good Example:** "<mark style="color:$success;">**cute grey bunny rabbit with big eyes**</mark>" (Defines a clear, isolated subject).
* **Bad Example:** "<mark style="color:$success;">**a blue sky with stars**</mark>" (An environment/background, not a single object).

#### Best Practices for Text

* **Be Specific:** Single nouns without descriptors (e.g., "table") are too broad and yield poor results. Instead, use descriptive phrasing (e.g., "<mark style="color:$success;">**round wooden coffee table**</mark>").
* **Length Matters:** Prompts that are at least 3 words long consistently produce the best results.
* **Use Style & Material Keywords:** Experiment with aesthetic keywords to guide the generation. Examples include: *Anime, Cyberpunk, Mid-Century Modern, Papercraft, Realistic/High Definition.*

{% hint style="info" icon="lightbulb-exclamation" %}
**Tip**: Don't be discouraged if your first generation isn't perfect. Try slightly rewording your description, or simply resubmit the same prompt to see a new variation.
{% endhint %}

<figure><img src="/files/2SwHcaq59WisbA0Ywl4Q" alt="" width="506"><figcaption></figcaption></figure>

### Image Prompts

For the best results, upload a high-quality image of an isolated object.

#### Technical Requirements

* **Aspect Ratio:** Square images (1:1) work best.
* **Dimensions:** The ideal image size is **1024 × 1024** pixels. Smaller images risk creating low-quality models, while higher-resolution images generally improve asset fidelity.

<figure><img src="/files/jsh0tJ5BidDOxYXU6SMH" alt=""><figcaption></figcaption></figure>

#### Composition Guidelines

| **Do** 👍                                                       | **Don't** **❌**                                                                  |
| --------------------------------------------------------------- | -------------------------------------------------------------------------------- |
| Center the object and ensure it is fully visible (not cropped). | Avoid busy or cluttered backgrounds that distract the generator.                 |
| Use a solid white background behind the object.                 | Avoid transparent backgrounds, as these can cause rendering artifacts.           |
| Focus on solid, well-defined shapes.                            | Avoid thin or entangled objects (e.g., fine wire mesh, intricate tree branches). |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://guide.404.xyz/404-gen-user-guide/getting-started/404-gen-prompt-guide.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.