404—GEN Prompt Guide

Your quick-start guide to generating high-quality 3D Models using optimised text prompts and ideal image inputs.

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: "cute grey bunny rabbit with big eyes" (Defines a clear, isolated subject).

• Bad Example: "a blue sky with stars" (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., "round wooden coffee table").

• 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.

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.

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.

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).