Tag
SenseNova U1.5-Lite-Preview is an open-source 8B MoT multimodal model that natively generates and edits ultra-wide panoramas, product posters, and commercial photography at 4K, with improved material rendering and fewer artifacts.
SenseNova released a preview of its U1.5 Lite model, showing benchmark gains in image generation and editing, with native 4K output and improved Chinese/English text rendering, though acknowledged weaknesses remain.
SenseNova U1 releases an infographic-specific finetune of its U1-8B-MoT base model, achieving significant benchmark improvements in infographic accuracy, chart understanding, and text rendering.
SenseNova U1 is a unified model that handles understanding, reasoning, and generation of text and images in the same architecture, enabling tasks like planning infographics end-to-end.
The article demonstrates how to use Sense Nova Skills, an AI tool, to generate a full global EV industry research report from a single prompt, with links to the GitHub repo and plugin.