Request invite
Research · 28 October 2026
Research

Hy‑Nomas introduces 8B diffusion model for free‑form interactive video world generation

The Hy‑Nomas model uses an 8‑billion‑parameter diffusion backbone to follow successive text instructions, maintain action‑aware causal attention, and provide continuous camera control across multiple interaction turns.

Why it matters

Benchmark Hy‑Nomas for multi‑turn video generation to inform roadmap decisions on interactive content features.

For product managers

For your product
What does this mean for your product?
Try it on your product
Read at Hugging Face Papers
More from this issueAll AI news from 28 Oct →
Google DeepMind launches Genie 4 world simulation model
Anthropic files S‑1 for proposed IPO on Nasdaq
Apple unveils iMac with M6 chip promising up to 18× Intel performanceAnnounced
Nvidia commits billions to AI accelerator supply chain, capacity from 2027

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an inviteSee how it works