--- id: "2026-10-21-tencent-hy-nomas-open-interactive-world-model" url: "https://postcutoff.com/e/2026-10-21-tencent-hy-nomas-open-interactive-world-model/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-10-21" date_precision: day category: open-source importance: 2 confidence: high status: [Confirmed] sources: 3 editor: human editor human_review: null version: "2026-10-27" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-10-21-tencent-hy-nomas-open-interactive-world-model/ # Tencent Hunyuan open-sources Hy-Nomas, an interactive video world model steered by text and camera, runnable on one RTX 4090 On Oct 21, 2026 Tencent's Hunyuan team published Hy-Nomas ("Towards Free-form Interactive World Generation") on GitHub and Hugging Face under Apache 2.0: a segment-autoregressive video world model that builds a scene one clip at a time from text instructions and camera trajectories, keeping context in a persistent KV cache, at 720×1280 and 24 fps with 8 distilled denoising steps. A low-memory INT8 configuration runs on a single RTX 4090; the team also released Hy-Nomas-Bench (280 test cases). No press coverage was found by Oct 26. ## Key facts - Repos: github.com/Tencent-Hunyuan/Hy-Nomas and huggingface.co/tencent/Hy-Nomas, both created Oct 21, 2026; a Diffusers port followed on Oct 24; Apache 2.0; ~206 GitHub stars on Oct 26 - Architecture (model card): segment-autoregressive diffusion transformer, Qwen text encoder, camera-conditioning modules and a PixelUMM video decoder (36 layers, 4,096 hidden); persistent KV cache between segments - Output: 720×1280 at 24 fps; distilled inference with 8 denoising steps (4 in the Diffusers example) - Interaction: multi-turn free-form instructions (add objects, change style or scene, describe actions) plus camera control - Hardware: standard setup uses 8-way sequence parallelism (eight GPUs); a single-GPU configuration with INT8 DiT, FP8 decoder, bounded 18-frame history and CPU offload targets one GeForce RTX 4090 - Benchmark: Hy-Nomas-Bench, four suites and 280 test cases (multi-turn text interaction, camera navigation, interleaved text and camera control, spatial memory); web demo at hy-nomas.hy.tencent.com ## What happened Tencent released, without a press push we could find, an open interactive world model in the same line as Google's Genie and Skywork's Matrix-Game: users "walk" a generated world by giving text instructions and camera paths, and the model extends the video segment by segment while remembering what it showed earlier. Weights, code, a Diffusers port and a benchmark are public. ## Why it matters Open world models that run on a consumer GPU are rare. This one comes from a major lab under a permissive licence. Its quality relative to Genie-class systems is unmeasured outside Tencent's own benchmark. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 143 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 113 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 204 days after its cutoff - Grok 4.7 (training cutoff May 2026): 143 days after its cutoff ## Sources 1. [Hugging Face: tencent/Hy-Nomas model card](https://huggingface.co/tencent/Hy-Nomas) (huggingface.co, official) 2. [GitHub: Tencent-Hunyuan/Hy-Nomas](https://github.com/Tencent-Hunyuan/Hy-Nomas) (github.com, code) 3. [Hugging Face: tencent/Hy-Nomas-Diffusers (Oct 24)](https://huggingface.co/tencent/Hy-Nomas-Diffusers) (huggingface.co, code) ## Changes - 2026-10-26 (filed): Created (found by a Hugging Face check of Chinese lab orgs; model card and repo read directly) ## Related - 2026-10-15: [Skywork releases Matrix-Game 4.0 world model](https://postcutoff.com/e/2026-10-15-skywork-matrix-game-4-open-source/index.md)