Prompt & Image Guide

The quality of your prompt (for Text-to-CAD) or source image (for Image-to-CAD) is the single biggest factor in output quality. This page covers what the pipeline handles well, what language patterns produce better results, and what to avoid.

Text-to-CAD Prompt Guide

Overview

Makistry is designed to handle any prompt, vague or specific. It interprets your idea, design intent, and thinks about them like an engineer would.

More information = Follows the specific requirements and constraints

Less information = Thinks independently and creatively

Simple Framework

Three-step framework for effective prompts:

1. High-level description: Describe your idea and the purpose of the design. A one-line description, problem you're trying to solve, or use cases can help guide the design in the right direction.
2. Outline components: List and briefly describe the components or features in your design.
3. Define constraints: Specify any dimensions, geometric requirements, or other design constraints.

Language Patterns That Produce Better Results

Be specific with dimensions — always include units:

✓  A 50×30×10mm rectangular plate
✗  A small flat plate

Name the feature type explicitly:

✓  An M5 counterbore: 8.5mm head diameter, 4.5mm deep, centered on the top face
✗  A screw hole on top

Specify the reference face or location:

✓  Two M4 through-holes on the long face, 15mm from each end, centered vertically
✗  Two holes on the side

Describe mating intent for assemblies:

✓  The lid sits on a 1.5mm step that runs around the inner perimeter of the base, with 0.15mm clearance
✗  The lid goes on the base

Use geometric vocabulary:

✓  Circular pocket, 20mm diameter, 5mm deep, centered on the top face
✗  A round dent in the top

Three Example Prompts at Different Levels of Complexity

VESA Mount Adapter

Make a 3 mm-thick adapter plate that lets a 75×75 mm VESA monitor mount attach to a 100×100 mm mount. Include 8 M4 through-holes and countersink the 75 mm pattern holes only. Add 0.7 mm chamfers.

Raspberry Pi Enclosure

Design a snap-fit enclosure for a 65 x 30 x 5 mm Raspberry Pi Zero, with ventilation slots on the top and a cutout for the micro-USB port on one side.

Spur Gear

Create a 20 mm-thick spur gear with 25 teeth, module of 2, and 10 mm-diameter central shaft hole.

Limitations

• Organic freeform surfaces: cloth, skin, terrain, splash forms, sculptural shapes
• Fluid or simulation geometry: anything that requires computational simulation to define shape
• Sub-0.1mm features: the kernel can represent them but the pipeline may not reliably produce them
• Assemblies with more than 8–10 distinct parts in standard or pro mode — switch to "assembly" mode, which parallelizes generation across parts

Image-to-CAD Source Image Guide

What Makes a Good Source Image

The image pipeline extracts edges, interprets geometry, and reconstructs a 3D B-rep model. The quality of that reconstruction depends almost entirely on how clearly the geometry is visible.

Best sources, in order of accuracy:

1. Hand sketches with labeled dimensions — much faster to produce than a photo
2. Orthographic photos (top, front, side) — supply multiple angles for 3D reconstruction
3. Perspective product photos — geometry is estimated from visible edges
4. Renders — useful when the physical part doesn't exist yet
5. Dimensioned engineering drawings — dimensions are read directly, so higher likelihood of missed features or dimensions

Ideal Image Conditions

• Single part per image (or a clearly dominant part)
• Clean background — white, light grey, or contrasting solid color
• High contrast between part edges and background
• Even lighting — avoid shadows that obscure edges or create false edges
• Sharp focus throughout the image — especially at edges
• Orthographic projection preferred over perspective; angled photos require the model to estimate foreshortening

Using Multiple Images

Submit up to 3 images of the same part from different viewpoints. Pair with a prompt hint to identify each view:

image 1: part_front.png
image 2: part_side.png  
image 3: part_top.png
prompt: "front view, right-side view, and top view of the same bracket"

Multi-view submissions significantly improve 3D reconstruction accuracy, particularly for parts with features that are only visible from certain angles.

Limitations

Resolution is rarely the problem. A sharp 800×600 image of a clean part will outperform a blurry 4K photo. Clarity and contrast matter more than megapixels.

Image vs. Drawing: Behavioral Differences