𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗨1.5-𝗟𝗶𝘁𝗲-𝗣𝗿𝗲𝘃𝗶𝗲𝘄.

An early open-source preview of our lightweight, natively unified multimodal model — built on the native NEO-Unify architecture to natively understand, reason, generate, and edit across modalities. 𝗪𝗶𝘁𝗵 𝗷𝘂𝘀𝘁 8𝗕-𝗠𝗼𝗧 𝗽𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿𝘀, 𝗶𝘁 𝗱𝗲𝗹𝗶𝘃𝗲𝗿𝘀 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗲𝗱𝗶𝘁𝗶𝗻𝗴 𝗾𝘂𝗮𝗹𝗶𝘁𝘆 𝘁𝗵𝗮𝘁 𝗿𝗶𝘃𝗮𝗹𝘀 𝗰𝗼𝗺𝗺𝗲𝗿𝗰𝗶𝗮𝗹 𝗰𝗹𝗼𝘀𝗲𝗱-𝘀𝗼𝘂𝗿𝗰𝗲 𝗺𝗼𝗱𝗲𝗹𝘀.

🌟This preview brings:
🔹𝗨𝗽 𝘁𝗼 4𝗞 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻, delivering richer details and fewer visual artifacts
🔹𝗦𝘁𝗿𝗼𝗻𝗴𝗲𝗿 𝗘𝗡/𝗖𝗡 𝘁𝗲𝘅𝘁 𝗿𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗮𝗻𝗱 𝗰𝗼𝗺𝗽𝗹𝗲𝘅 𝗹𝗮𝘆𝗼𝘂𝘁 𝗰𝗼𝗺𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻
🔹𝗠𝗼𝗿𝗲 𝗽𝗿𝗲𝗰𝗶𝘀𝗲 𝘃𝗶𝘀𝘂𝗮𝗹 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 with long, multi-constraint prompts
🔹𝗠𝗼𝗿𝗲 𝗿𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗻𝗮𝘁𝗶𝘃𝗲 𝗶𝗺𝗮𝗴𝗲 𝗲𝗱𝗶𝘁𝗶𝗻𝗴 across reference-guided style transfer, multi-reference composition, local infographic editing and text editing

🌟Improvements over U1 on generation & editing benchmarks:
🔹Qwen-Image-Bench: 47.14 → 55.20 (w/ PE)
🔹ImgEdit-Bench: 3.90 → 4.37
🔹GEdit-Bench-en: 7.47 → 8.17
🔹GEdit-Bench-zh: 7.42 → 8.05

From U1 to U1.5, this open-source journey reflects our continued innovation at the foundation-model level. Meanwhile, U1 Pro, our production-ready model for creators, will open for public access soon.

🛠️ GitHub: https://github.com/OpenSenseNova/SenseNova-U1/blob/feat/u1.5_preview/docs/u1.5_preview.md
🤗 Hugging Face: https://huggingface.co/sensenova/SenseNova-U1.5-8B-MoT-Preview
👾 Discord: https://discord.com/invite/BuTXPHmQub