Hy-Nomas
Type: RepoCategory: Generation★ new (GitHub, when we checked)Spotted, not yet tested
Hy-Nomas is an open-source repo in our Generation category. Tencent Hunyuan's open interactive video world model: generates segment by segment and takes new text prompts or camera trajectories between turns, with a lifelong KV cache for consistency. 8-step distilled inference, 720×1280 at 24 fps, Cinematic and Robotics LoRAs, Nomas-PE prompt enhancer, single-RTX 4090 low-memory config (INT8/FP8, CPU offload), LoRA fine-tune recipe. CUDA 13. Weights on HF. Apache-2.0.
Where it fits: Open-weight video & audio models.
Listing isn’t endorsement. This is our summary of the project’s own docs, not a Studio Hall test result. Check the licence and requirements at the source before you build on it.
Lab posts that cover Hy-Nomas
- Tencent Hy-Nomas: an open interactive video world model you steer as it rendersSpotted, not yet tested
Related Lab posts
- LTX Desktop 1.3.1: green-screen-free cutouts, drawn motion paths, 4K and a planning assistant in the free local appSpotted, not yet tested
- #OpenSourceHiggsfield: Comfy's $25K challenge and the first open rebuildsSpotted, not yet tested
- The top GitHub video repos right now, ranked by stars (Oct 2026)Spotted, not yet tested
- An open-source audio stack for video: music, foley, lip-sync, timingSpotted, not yet tested
- EffectCraft: an open-source, After Effects-style compositor in pure Rust that agents can drive over MCPSpotted, not yet tested
Similar skills & repos
- LTX Desktop · Repo, Generation
- Comfield · Repo, Generation
- LTX-Video · Repo, Generation
- Wan 3.0 (official) · Repo, Generation
- prompt2rig · Repo, Generation
- Node Banana · Repo, Generation