𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗨𝟭.𝟱 𝗟𝗶𝘁𝗲 — 𝗦𝗵𝗮𝗿𝗽𝗲𝗿. 𝗠𝗼𝗿𝗲 𝗖𝗼𝗻𝘁𝗿𝗼𝗹𝗹𝗮𝗯𝗹𝗲. 𝗠𝗼𝗿𝗲 𝗖𝗼𝘀𝘁-𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁. An 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲, lightweight native unified multimodal model for visual understanding, generation & editing. 𝗕𝘂𝗶𝗹𝘁 𝗳𝗼𝗿 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝘃𝗶𝘀𝘂𝗮𝗹 𝗮𝗿𝘁𝗶𝗳𝗮𝗰𝘁 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀: 🔹𝗡𝗮𝘁𝗶𝘃𝗲 𝟰𝗞 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 with better detail, composition & realism 🔹𝗖𝗼𝗺𝗽𝗹𝗲𝘅 𝗶𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗼𝗹𝗹𝗼𝘄𝗶𝗻𝗴 across subjects, counts, text, layouts & styles 🔹𝗘𝗻𝗵𝗮𝗻𝗰𝗲𝗱 𝗖𝗵𝗶𝗻𝗲𝘀𝗲/𝗘𝗻𝗴𝗹𝗶𝘀𝗵 𝘁𝗲𝘅𝘁 𝗿𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 & 𝗺𝘂𝗹𝘁𝗶-𝘁𝗲𝘅𝘁 𝗹𝗮𝘆𝗼𝘂𝘁 🔹𝗣𝗿𝗲𝗰𝗶𝘀𝗲 𝗶𝗺𝗮𝗴𝗲 𝗲𝗱𝗶𝘁𝗶𝗻𝗴 & 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 with visual markers, bounding boxes & multi-image references Just 𝟴𝗕 parameters — outperforming same-size models in instruction following and editing preservation, while 𝗰𝗼𝗺𝗽𝗲𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗹𝗮𝗿𝗴𝗲 𝗰𝗼𝗺𝗺𝗲𝗿𝗰𝗶𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀 𝗶𝗻 𝘁𝗲𝘅𝘁 𝗿𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗮𝗻𝗱 𝗰𝗼𝗺𝗽𝗹𝗲𝘅 𝗹𝗮𝘆𝗼𝘂𝘁𝘀. 🛠️GitHub: 🤗HF: 👾Discord: 🎨SenseNova Studio:

𝗢𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗶𝗻𝗴 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮-𝗩𝗶𝘀𝗶𝗼𝗻-7𝗕-𝗠𝗼𝗧 — 𝗼𝗻𝗲 𝗺𝗼𝗱𝗲𝗹, 𝗮𝗹𝗹 𝗺𝗮𝗷𝗼𝗿 𝘃𝗶𝘀𝗶𝗼𝗻 𝘁𝗮𝘀𝗸𝘀. Reimagines CV as multimodal generation. Steerable by language or visual prompts. 𝗡𝗼 𝘁𝗮𝘀𝗸-𝘀𝗽𝗲𝗰𝗶𝗳𝗶𝗰 𝗵𝗲𝗮𝗱𝘀 — 𝘀𝘁𝗶𝗹𝗹 𝗦𝗢𝗧𝗔, 𝘀𝘂𝗿𝗽𝗮𝘀𝘀𝗶𝗻𝗴 𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗲𝗲𝗽𝗠𝗶𝗻𝗱'𝘀 𝗩𝗶𝘀𝗶𝗼𝗻 𝗕𝗮𝗻𝗮𝗻𝗮 𝗼𝗻 𝘀𝗲𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗱𝗲𝗻𝘀𝗲 𝗴𝗲𝗼𝗺𝗲𝘁𝗿𝘆. 📊 𝘃𝘀. 𝗩𝗶𝘀𝗶𝗼𝗻 𝗕𝗮𝗻𝗮𝗻𝗮 (𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗲𝗲𝗽𝗠𝗶𝗻𝗱): 🔹Referring segmentation (RefCOCOg cIoU): 80.3 vs 73.8 🔹Semantic segmentation (Cityscapes mIoU): 71.2 vs 69.9 🔹Depth estimation (NYUv2 δ1): 98.1 vs 94.8 🔹Surface normal (NYUv2 mean error): 14.4 vs 17.8 Built on a decade of SenseTime's CV leadership — #1# in China's Vision AI market for 10 consecutive years, and named a Tech Innovator in global GenAI CV by Gartner. 𝗩𝗶𝘀𝗶𝗼𝗻, 𝗻𝗼𝘄 𝗻𝗮𝘁𝗶𝘃𝗲 𝘁𝗼 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀. New tasks, defined by instruction — not by new model heads.