Use Cases Compare Learn Blog Docs Open Studio

From Text to 3D Model in 30 Seconds

Text-to-3D was one of the earliest AI 3D demos. The 2024 generation was rough — sometimes 90 seconds, sometimes 5 minutes, sometimes a melted-looking mess. The 2026 generation is fast and good.

Yugma uses Meshy as the text-to-3D backend, integrated as the Generation panel in the studio. You don't leave the editor.

How it works

When you need a real-world object that isn't in the Sketchfab library — a custom-branded item, an unusual prop, a stylized variant — you generate it in the Text-to-3D (Generation) panel, which calls Meshy's API. The result lands in the scene as a normal scene-graph object, and the AI Director can place, scale, and restyle it from there.

Typical timing:

When to generate vs import

The decision tree (simplified):

  1. Do you want a real-world object? Yes → continue.
  2. Is it findable in Sketchfab with reasonable quality? Yes → let the AI Director import it via import_from_sketchfab (free, instant).
  3. No → generate it in the Text-to-3D panel (Meshy), then ask the Director to place it.

This keeps costs sane. Sketchfab is free; Meshy generations are credit-metered. Prefer Sketchfab when a good model exists — the AI Director does.

Free tier vs paid

Quality

Meshy ships a few model variants:

For most scene work, default is right. For hero assets, prefer the higher-fidelity variant on a paid plan or generate in Meshy directly with their full settings.

What it can't do

When to use Sketchfab instead

Most everyday objects (chairs, tables, lamps, plants, cars, animals) already exist in Sketchfab, often free under CC. Faster, no credit cost, often higher quality. The AI prefers Sketchfab automatically.

When to use Meshy directly

If you need batch asset generation (50+ unique items for a game), use the Meshy app directly with their full controls — Yugma's in-studio Text-to-3D panel is for one-at-a-time scene composition, not asset farming.

What's next

Read the text-to-3d feature page →