{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-10-21-tencent-hy-nomas-open-interactive-world-model/","md":"https://postcutoff.com/e/2026-10-21-tencent-hy-nomas-open-interactive-world-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-21-tencent-hy-nomas-open-interactive-world-model","date":"2026-10-21","date_precision":"day","short_title":"Tencent Hunyuan open-sources Hy-Nomas, an interactive video world model steered by text and camera, runnable on one RTX 4090","deck":null,"takeaway":"A low-memory INT8 configuration runs on a single RTX 4090; the team also released Hy-Nomas-Bench (280 test cases).","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Hugging Face: tencent/Hy-Nomas model card","url":"https://huggingface.co/tencent/Hy-Nomas","type":"official","group":"primary","domain":"huggingface.co"},{"n":2,"title":"GitHub: Tencent-Hunyuan/Hy-Nomas","url":"https://github.com/Tencent-Hunyuan/Hy-Nomas","type":"code","group":"primary","domain":"github.com"},{"n":3,"title":"Hugging Face: tencent/Hy-Nomas-Diffusers (Oct 24)","url":"https://huggingface.co/tencent/Hy-Nomas-Diffusers","type":"code","group":"primary","domain":"huggingface.co"}],"official":3,"filed":"2026-10-26","updated":"2026-10-26","orgs":["Tencent"],"title":"Tencent Hunyuan open-sources Hy-Nomas, an interactive video world model steered by text and camera, runnable on one RTX 4090","summary":"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"],"key_numbers":[],"tags":["world-model","video-generation","open-weights","china","apache-2.0","hunyuan"],"science":null,"body_md":"## What happened\n\nTencent released, without a press push we could find, an open interactive world model in the same line as Google's Genie and Skywork's\nMatrix-Game: users \"walk\" a generated world by giving text instructions and camera paths, and the model extends the video segment by\nsegment while remembering what it showed earlier. Weights, code, a Diffusers port and a benchmark are public.\n\n## Why it matters\n\nOpen world models that run on a consumer GPU are rare. This one comes from a major lab under a permissive licence. Its quality relative\nto Genie-class systems is unmeasured outside Tencent's own benchmark.","disputed":[],"related":[{"id":"2026-10-15-skywork-matrix-game-4-open-source","url":"https://postcutoff.com/e/2026-10-15-skywork-matrix-game-4-open-source/","date":"2026-10-15","date_precision":"day","short_title":"Skywork releases Matrix-Game 4.0 world model","deck":null,"takeaway":"The \"engine plus neural renderer\" split is a practical answer to the consistency problems of video world models, and running on one consumer GPU makes it usable by hobbyists.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"filed":"2026-10-15","updated":"2026-10-15","orgs":["Skywork AI","Kunlun Tech"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-26","type":"filed","text":"Created (found by a Hugging Face check of Chinese lab orgs; model card and repo read directly)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-26","run":null,"sources_read":"Found by a Hugging Face check of Chinese lab orgs; model card and repo read directly","updated":"2026-10-26","human_review":null,"version":{"date":"2026-10-27"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":143,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":113,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":204,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":143,"in_training_data":false}],"short_url":null}