WanGP v18.81 adds Tencent's Hy-Nomas world model, playable on 8GB VRAM
cocktailpeanut · x · 2026-10-27
WanGP (11.1k GitHub stars) ships v18.81 "The One World Generator", adding Tencent's Hy-Nomas world model: build a world from text (or from an image via EVOKE), then explore it with WASD and text prompts — saveable, recordable, revisitable — starting at 8GB VRAM thanks to MMGP v4.
- Hy-Nomas (text-to-world) and EVOKE (image-to-world); realtime expected on 24GB+ VRAM, non-realtime on 8GB
- Local agent "Deepy Prime" gets 2x context at same VRAM, plus web search for LoRAs, Python batch graphics workflows, 3D asset generation, and video restore/upscale/outpaint
- 1-click launch via Pinokio
Related event: WanGP v18.81 Adds Hy-Nomas World Model, Runs on 8GB VRAM(2 posts)→
More from Embodied
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27
- Tesla FSD approved in Latvia, the 10th European country; Musk praises smaller nations for moving fastest — elonmusk · 2026-10-27
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27