SenseTime has announced the open-source preview of its lightweight, unified multimodal model SenseNova U1.5-Lite-Preview. Based on the NEO-unify architecture, the model achieves native 4K image generation, more detailed texture expression, more accurate Chinese and English text generation, and more stable image editing capabilities with an 8B-MoT parameter scale. The model improves understanding of long natural language descriptions and structured visual instructions, enabling more precise visual control. In image editing, it supports style transfer from reference images, combined editing with multiple reference images, and interactive precise adjustment. Compared to the previous generation model, U1.5-Lite-Preview has achieved improvements in multiple evaluation benchmarks, balancing generation quality and interaction capabilities with a smaller model size. The model is available for download on GitHub, Hugging Face, and ModelScope community for developers and researchers. Additionally, the delivery-level creative model SenseNova U1Pro is in a tight invitation testing phase. The open-source release reflects the industry trend of shifting from parameter scale to efficiency, control capability, and practical application experience.