{"name":"Hy-Nomas","repo":"Tencent-Hunyuan/Hy-Nomas","url":"https://midorreal.com/project/tencent-hunyuan-hy-nomas","repository":"https://github.com/Tencent-Hunyuan/Hy-Nomas","description":"Hy-Nomas: Towards Free-form Interactive World Generation","facts":{"language":{"value":"Python","source":"https://github.com/Tencent-Hunyuan/Hy-Nomas","checked":"21 Nov 2026"},"releases":{"value":"0","source":"https://github.com/Tencent-Hunyuan/Hy-Nomas/releases","checked":"20 Nov 2026"},"contributors":{"value":"16","source":"https://github.com/Tencent-Hunyuan/Hy-Nomas/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/Tencent-Hunyuan/Hy-Nomas","checked":"21 Nov 2026"}},"stars":603.0,"writeup":{"what_it_is":"Hy-Nomas is a free-form interactive world generation model controlled by multi-turn text and camera inputs. The repository provides training, inference, an interactive demo, and data annotation code.","audience":"Researchers and developers building interactive video world generation","claims":[{"kind":"specific","claim":"Runs on a single RTX 4090 with low-memory inference","excerpt":"It runs on a single RTX 4090 with low-memory inference","status":"not_checked"},{"kind":"specific","claim":"Supports LoRA fine-tuning for downstream tasks","excerpt":"supports LoRA fine-tuning for downstream tasks","status":"not_checked"},{"kind":"specific","claim":"Inference uses 4-8 denoising steps with a finetuned PixelUMM decoder","excerpt":"Inference uses 4-8 denoising steps and a finetuned PixelUMM decoder","status":"not_checked"},{"kind":"specific","claim":"Includes an interactive web demo that generates across multiple turns","excerpt":"A web interface supports generation across multiple turns and decoding at segment boundaries.","status":"not_checked"},{"kind":"broad","claim":"Supports free-form prompt control for imaginary objects, styles, scenes, and actions","excerpt":"Control the world generation with any kind of free form user prompt","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-16"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":54,"reality":61,"gap":-7,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-21T03:04:54+00:00","text":"Repository created","source":"https://github.com/Tencent-Hunyuan/Hy-Nomas"}],"cite":"Hy-Nomas is a GitHub project at https://github.com/Tencent-Hunyuan/Hy-Nomas written mainly in Python, described there as \"Hy-Nomas: Towards Free-form Interactive World Generation\".","attribution":"Data from Mid or Real, https://midorreal.com/project/tencent-hunyuan-hy-nomas, checked 22 November 2026. Attribution with a link is required.","still_real":null}