SenseTime Releases SenseNova-U1.5, an 8B Encoder-Free Unified Multimodal Model

SenseTime has released SenseNova-U1.5, an 8B unified multimodal model that performs visual understanding, reasoning and image generation without external encoders or VAEs. The model supports 4K resolution and is now available on Hugging Face.

2026-09-11 ~ 2026-09-11 · 2 related posts