Skip to content
IFAI

Generative media

Tripo's new 3D generator builds game-ready quads

Published Reach 37

Tripo just dropped P2.0 Preview, a 3D asset generator built specifically for games and real-time pipelines. It features native quad topology supporting up to 50,000 triangles or 25,000 quads, delivering clean edge loops around joints and smooth flat surfaces. Every user gets two free generations to test it out.

Tripo's new 3D generator builds game-ready quads
Image: x.com

Anyone who works in 3D knows the dirty secret of AI models: they look great in a screenshot, but the mesh is usually a chaotic mess of triangles that no game engine wants to touch.

Tripo's new P2.0 Preview aims to fix that. Built specifically for games and real-time production pipelines, the update introduces native quad topology right out of the box.

Clean meshes without manual retopology

The generator supports up to 50,000 triangles or 25,000 quads.

Instead of unstructured geometry, P2.0 outputs smooth edge loops around joints and clean, orderly quads across flat surfaces.

Tripo highlights that the model works best for game characters, hard-surface props, mechanical assemblies, weapons, and vehicles. It is geared toward studios that need to crank out high volumes of usable assets quickly.

Every user gets two free generations to test it out. Meanwhile, Tripo P1.0 has graduated to general availability for all users, with annual subscriptions discounted by up to 50%.

Why it matters

Automated 3D generation has spent the last year stuck in the concept phase because production teams had to spend hours manually retopologizing every asset.

By generating native quads, Tripo is removing one of the biggest bottlenecks between AI generation and actual in-engine deployment. We think this is a huge quality-of-life win for indie developers and small studios trying to stretch limited art budgets.

The 25,000-quad limit means this won't replace hero-grade character sculpting just yet, and we still need to see how cleanly those joint loops hold up under heavy rigging deformation. But for background props, vehicles, and rapid prototyping, it looks ready to bypass the retopology chore entirely.

Sources (1)

  1. [1]
    x.com(opens in a new tab)Originalx.com

Best of AI, daily