✦
Summary
SenseNova-U1.5-8B-MoT is a native unified multimodal model for image understanding, text-to-image generation, and image editing. It is designed to improve visual quality, text rendering, layout control, and preservation of subjects and unedited regions.
Key Features
Native unified multimodal architecture.
Text-to-image generation.
Image understanding and editing.
Native 4K image generation.
Improved Chinese and English text rendering.
Local and multi-reference edits.
Bounding-box and visual-marker control.
Apache 2.0 public model weights.
About SenseNova-U1.5-8B-MoT
The model is built on the NEO-unify architecture and improves patchify layers, data quality, prompt enhancement, task formulation, and post-training. It supports native 4K generation, local and multi-reference editing, object and region control, and complex instructions involving counts, spatial relationships, styles, and layouts.
Released with public weights and an Apache 2.0 license, SenseNova-U1.5 can be run through its reference inference repository or tried in SenseNova Studio. It is useful for posters, infographics, brand assets, creative image generation, and controlled image editing.