OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 72
Running on Zero Agents Featured 897 OmniVoice 🌍 897 High-quality voice cloning TTS for 600+ languages
Running on Zero MCP 1.31k Wan2.2 14B Fast Preview 🐌 1.31k generate a video from an image with a text prompt
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome Paper • 2603.28407 • Published Mar 30 • 70
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing Paper • 2603.28713 • Published Mar 30 • 22