Running on Zero Agents Featured 134 MiniMax H3 π¬ 134 Video generation with a synchronized soundtrack
Running on Zero Agents 1 SymphonyGen Demo π» 1 Orchestral generation controlled by a harmony skeleton
Running on Zero MCP 3 QueenVIS Video Instance Segmentation π 3 Segment and track object instances in video with QueenVIS
Running on Zero MCP 32 BS-Roformer Leap Audio Separator π΅ 32 Separate audio into vocals and instruments with BS-Roformer
Running on Zero Agents Featured 98 Mage-VL π 98 Codec-native video & image understanding with Mage-VL 4B
Running on Zero MCP 14 WordVoice Word-Level Controllable TTS π£ 14 Zero-shot TTS with explicit word-level prosody control
Runtime error MCP Featured 125 Mage-Flow π¨ 125 Efficient native-resolution image generation and editing
Running on Zero MCP 6 MonkeyOCRv2 Document Parser π 6 Parse document images into structured Markdown
Running on Zero Agents Featured 100 OvisOCR2 π 100 Stream structured Markdown from document images and PDFs.
Running on Zero MCP 6 OvisOCR2 Document to Markdown π 6 Parse document images into Markdown with OvisOCR2
Running on CPU Upgrade Agents 4 Conference Paper Search π 4 Search accepted papers across ML conferences
Running on Zero MCP Featured 74 UniSE Speech Enhancement π 74 Unified AR-LM-based speech enhancement & separation
Running Featured 508 HF Realtime Voice π 508 Voice chat over WebSocket against a HF speech-to-speech
Running on CPU Upgrade Agents 122 MMEB Leaderboard π 122 The massive multimodal embedding benchmark