𝗨𝗻𝘃𝗲𝗶𝗹𝗶𝗻𝗴 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗨1 𝗣𝗿𝗼 SenseTime’s flagship native multimodal foundation model. Built on the 𝗡𝗘𝗢-𝗨𝗻𝗶𝗳𝘆 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲, U1 Pro unifies 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴, 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻, 𝗮𝗻𝗱 𝗮𝗰𝘁𝗶𝗼𝗻 with 𝗻𝗮𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗹𝗲𝗮𝘃𝗲𝗱 𝘃𝗶𝘀𝗶𝗼𝗻-𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴. The unification of these capabilities lays a 𝗰𝗿𝘂𝗰𝗶𝗮𝗹 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗰𝗼𝗺𝗽𝗹𝗲𝘅 𝘃𝗶𝘀𝘂𝗮𝗹 𝗰𝗿𝗲𝗮𝘁𝗶𝗼𝗻. Over years, AI image creation has evolved from visuals that look right, to details that feel real. U1 Pro takes the next step by 𝗯𝗿𝗶𝗻𝗴𝗶𝗻𝗴 𝗽𝗿𝗼𝗳𝗲𝘀𝘀𝗶𝗼𝗻𝗮𝗹 𝗱𝗲𝘀𝗶𝗴𝗻 𝗮𝗲𝘀𝘁𝗵𝗲𝘁𝗶𝗰𝘀 𝘁𝗼 𝘁𝗵𝗲 𝗶𝗺𝗮𝗴𝗲 as a whole. Key upgrades over SenseNova U1 Lite: ✨ Native 𝗹𝗼𝗻𝗴-𝗵𝗼𝗿𝗶𝘇𝗼𝗻 𝗶𝗻𝘁𝗲𝗿𝗹𝗲𝗮𝘃𝗲𝗱 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 across dozens of rounds in an 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗟𝗼𝗼𝗽 ✨ Enhanced capabilities in 𝗶𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗻𝗴 𝗮𝗻𝗱 𝗮𝗻𝗮𝗹𝘆𝘇𝗶𝗻𝗴 𝘁𝗲𝘅𝘁𝘂𝗮𝗹 𝗮𝗻𝗱 𝘃𝗶𝘀𝘂𝗮𝗹 𝗶𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 ✨ 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 𝗼𝘃𝗲𝗿 𝘁𝗲𝘅𝘁 𝗮𝗻𝗱 𝗶𝗺𝗮𝗴𝗲 𝗱𝗲𝘁𝗮𝗶𝗹𝘀, with a very low error rate in rendered texts ✨ Up to 8𝗞 𝗻𝗮𝘁𝗶𝘃𝗲 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻 output ✨ Enables 𝘂𝗹𝘁𝗿𝗮-𝘄𝗶𝗱𝗲 and 𝘂𝗹𝘁𝗿𝗮-𝘁𝗮𝗹𝗹 image creation From 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻𝘀 and 𝗯𝗿𝗮𝗻𝗱 𝗺𝗮𝗿𝗸𝗲𝘁𝗶𝗻𝗴 to 𝗲𝗱𝘂𝗰𝗮𝘁𝗶𝗼𝗻, 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗶𝗻𝗴, 𝗳𝗶𝗹𝗺, 𝗮𝗻𝗶𝗺𝗮𝘁𝗶𝗼𝗻, and 𝗱𝗶𝗴𝗶𝘁𝗮𝗹 𝗰𝗼𝗻𝘁𝗲𝗻𝘁 𝗰𝗿𝗲𝗮𝘁𝗶𝗼𝗻, U1 Pro empowers creators across industries. 💻 Preview (invite-only) available now. 📅 Official launch with API + pricing: August 2026. ✨Newly Added✨ 𝗟𝗲𝗮𝗿𝗻 𝗺𝗼𝗿𝗲 𝗮𝗯𝗼𝘂𝘁 𝗼𝘂𝗿 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗨1 𝗦𝗲𝗿𝗶𝗲𝘀: https://github.com/OpenSenseNova/SenseNova-U1

Looks like another high-quality model release happened in China yesterday that no one in my timeline is talking about. U1 Pro from SenseTime seems to give GPT image 2 and Seed Dream a run for their money. Feature details in reply. https://twitter.com/sensetime_ai/status/2078681943680704993