NOVA Collection NOVA: Autoregressive Video Generation without Vector Quantization • 6 items • Updated about 8 hours ago • 5
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands Paper • 2512.24965 • Published Dec 31, 2025 • 42
Running on Zero Featured 1.21k Qwen3-TTS Demo 🎙 1.21k Transform text into natural-sounding speech with custom voices
view article Article Introducing Waypoint-1: Real-time interactive video diffusion from Overworld +3 16 days ago • 35
Paused Featured 61 Waypoint 1 Small 🎮 61 Explore and navigate through AI-generated worlds in real-time
Skywork-Unipic3 Collection Unified Multi-Image Composition with Sequence Modeling • 7 items • Updated about 11 hours ago • 10
view post Post 1677 Check out Orpheus Karaoke! Turn any MIDI into a unique Karaoke MIDI! projectlosangeles/Orpheus-Karaoke See translation 🔥 3 3 ❤️ 3 3 + Reply
HeartMuLa: A Family of Open Sourced Music Foundation Models Paper • 2601.10547 • Published 20 days ago • 41