How Microsoft’s WHAMM Uses AI to Render Gameplay in Real Time

How Microsoft’s WHAMM Uses AI to Render Gameplay in Real Time

Microsoft’s WHAMM model renders real-time game frames using AI instead of a graphics engine. Trained on just one week of Quake II footage, it predicts each frame from player input, opening the door to a future of interactive, AI-generated worlds.
10 mins read
May 12, 2025
Share

Traditional game graphics are built through simulation: every shadow is calculated, every polygon is mapped, and every collision is modeled using hardcoded rules.

But what if we skipped the simulation entirely?

What if, instead of calculating every detail through physics and rendering engines, an AI model could predict the game’s next frame, based purely on learned patterns from gameplay?

That’s the promise of a new direction in Generative AI: systems that don’t just create static content like art or text, but generate dynamic, interactive environments. At the cutting edge of that idea is WHAMM, a project from Microsoft Research.

Today, I'll share:

  • What WHAMM is (and why it matters)

  • How WHAMM works under the hood

  • WHAMM vs. WHAM: A performance leap

Let's get started.

The Educative Newsletter
Speedrun your learning with the Educative Newsletter
Level up every day in just 5 minutes!
Level up every day in just 5 minutes. Your new skill-building hack, curated exclusively for Educative subscribers.
Tech news essentials – from a dev's perspective
In-depth case studies for an insider's edge
The latest in AI, System Design, and Cloud Computing
Essential tech news & industry insights – all from a dev's perspective
Battle-tested guides & in-depth case studies for an insider's edge
The latest in AI, System Design, and Cloud Computing

Written By:
Fahim ul Haq
Free Edition
OpenAI's o3-mini: Is it worth trying as a developer?
Is the o3-mini a worthwhile alternative to DeepSeek's accuracy and performance? We break down its strength and compare it with R1.
7 mins read
Feb 24, 2025