商汤SenseTime发布推文，感谢YouTuber xCreate对SenseNova U1模型的详细拆解，重点展示其文本-图像交错推理（text-image interleaved reasoning）和信息图表（infographic）生成能力。推文附有逐步指南，指导用户通过SenseNova Studio在线使用或本地运行模型。相关资源包括YouTube视频、HuggingFace模型集合、GitHub仓库及Discord社区链接。
Thanks YouTuber xCreate for the great breakdown of 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗨1! Great to see the model's powerful 𝘁𝗲𝘅𝘁-𝗶𝗺𝗮𝗴𝗲 𝗶𝗻𝘁𝗲𝗿𝗹𝗲𝗮𝘃𝗲𝗱 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 and 𝗶𝗻𝗳𝗼𝗴𝗿𝗮𝗽𝗵𝗶𝗰 capabilities featured — along with a 𝘀𝘁𝗲𝗽-𝗯𝘆-𝘀𝘁𝗲𝗽 𝗴𝘂𝗶𝗱𝗲 𝘁𝗼 𝗿𝘂𝗻𝗻𝗶𝗻𝗴 𝗶𝘁 𝗹𝗼𝗰𝗮𝗹𝗹𝘆 𝗮𝗻𝗱 𝘃𝗶𝗮 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗦𝘁𝘂𝗱𝗶𝗼.
🎥https://www.youtube.com/watch?v=FWaQC_exKh0
🎛️SenseNova Studio: https://unify.light-ai.top (Try infographics; also join Discord for text-image interleaved gen)
🤗https://huggingface.co/collections/sensenova/sensenova-u1
🛠️https://github.com/OpenSenseNova/SenseNova-U1
👾Discord: https://discord.com/invite/BuTXPHmQub
来源：SenseTime · x.com