OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 72
Running on Zero Agents Featured 1.01k OmniVoice 🌍 1.01k High-quality voice cloning TTS for 600+ languages
Running on Zero MCP 1.64k Wan2.2 14B Fast Preview 🐌 1.64k 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 • 71
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing Paper • 2603.28713 • Published Mar 30 • 23