Home
SenseTime Unveils 8B Lightweight Multimodal Model with Native 4K Output and Full Visual Editing Capabilities
SenseTime has officially released SenseNova U1.5Lite, a new lightweight, native unified multimodal large model. With 8B parameters, this efficient model outperforms similarly sized alternatives in key visual tasks and matches large-scale commercial models in complex layout and text rendering scenarios.

Supporting context lengths of 3K to 4K natively, SenseNova U1.5Lite manages multiple constraints—including subject, quantity, spatial relationships, text, layout, and style—simultaneously, ensuring greater stability for complex visual operations.
The model introduces several core upgrades. First, it delivers higher-quality visual generation by improving composition, color, material, lighting, realism, and local details, effectively preventing the common issue of locally correct but globally incomplete outputs. Second, it offers robust native image editing, better preserving subject identity, spatial structure, layout, and non-editable areas while enhancing local modifications, element replacement, text refinement, and multi-reference editing.

Furthermore, the model excels in handling text and complex layouts, strengthening its capabilities in Chinese and English text, posters, infographics, brand visuals, and multi-text formatting to achieve complete visual expression. For precise control, it supports Bounding Box, Visual Marker, and single or multi-image references. Notably, it achieves native 4K high-resolution output, maintaining both macro composition and fine textures, small text, and lighting effects.
Project address: https://github.com/OpenSenseNova/SenseNova-U1
Related article
Claude Unveils First Full Ultraviolet Sky Map, Charting 119 Million Stars
With the powerful assistance of Claude, Anthropic’s large language model, astrophysicists have successfully generated the first complete ultraviolet all-sky map in history. This vast star chart, featuring 119 million stars, was largely completed by C
How AWS and NVIDIA Are Powering Agentic and Physical AI
NVIDIA CEO Jensen Huang (Credit: Tomohiro Ohsumi/Getty Images)Jensen Huang’s NVIDIA and AWS scale their global partnership, deploying 2M GPUs to power next-generation agentic and physical AI enterprise infrastructureAWS and NVIDIA have announced a ma
Brainwave Training Robot: Physical AI’s Next Leap Driven by Human Brain Signals
In a San Leandro, California warehouse, Encord, a data tools firm, is running an innovative experiment: "pilots" wear headsets with cameras and EEG sensors while playing Jenga to capture brain activity. The Zander Labs EEG headset tracks brainwaves i
Related Special Topic Recommendations
Comments (0)
0/500
SenseTime has officially released SenseNova U1.5Lite, a new lightweight, native unified multimodal large model. With 8B parameters, this efficient model outperforms similarly sized alternatives in key visual tasks and matches large-scale commercial models in complex layout and text rendering scenarios.

Supporting context lengths of 3K to 4K natively, SenseNova U1.5Lite manages multiple constraints—including subject, quantity, spatial relationships, text, layout, and style—simultaneously, ensuring greater stability for complex visual operations.
The model introduces several core upgrades. First, it delivers higher-quality visual generation by improving composition, color, material, lighting, realism, and local details, effectively preventing the common issue of locally correct but globally incomplete outputs. Second, it offers robust native image editing, better preserving subject identity, spatial structure, layout, and non-editable areas while enhancing local modifications, element replacement, text refinement, and multi-reference editing.

Furthermore, the model excels in handling text and complex layouts, strengthening its capabilities in Chinese and English text, posters, infographics, brand visuals, and multi-text formatting to achieve complete visual expression. For precise control, it supports Bounding Box, Visual Marker, and single or multi-image references. Notably, it achieves native 4K high-resolution output, maintaining both macro composition and fine textures, small text, and lighting effects.
Project address: https://github.com/OpenSenseNova/SenseNova-U1
Claude Unveils First Full Ultraviolet Sky Map, Charting 119 Million Stars
With the powerful assistance of Claude, Anthropic’s large language model, astrophysicists have successfully generated the first complete ultraviolet all-sky map in history. This vast star chart, featuring 119 million stars, was largely completed by C
How AWS and NVIDIA Are Powering Agentic and Physical AI
NVIDIA CEO Jensen Huang (Credit: Tomohiro Ohsumi/Getty Images)Jensen Huang’s NVIDIA and AWS scale their global partnership, deploying 2M GPUs to power next-generation agentic and physical AI enterprise infrastructureAWS and NVIDIA have announced a ma
Brainwave Training Robot: Physical AI’s Next Leap Driven by Human Brain Signals
In a San Leandro, California warehouse, Encord, a data tools firm, is running an innovative experiment: "pilots" wear headsets with cameras and EEG sensors while playing Jenga to capture brain activity. The Zander Labs EEG headset tracks brainwaves i











