SenseTime Releases SenseNova U1.5: 8B Open Model with Native 4K Generation
liuziwei7 · x · 2026-08-21
SenseTime has released SenseNova U1.5 Lite, an open-source, lightweight native unified multimodal model. Despite having only 8B parameters (MoT architecture), it emphasizes high controllability and cost-effectiveness.
Key Features:
- Native 4K Generation: Supports high-resolution output with improved detail, composition, and realism.
- Complex Instruction Following: Capable of handling complex combinations of subjects, counts, text, layouts, and styles.
- Precise Editing & Control: Supports image editing using visual markers, bounding boxes, and multi-image references.
- Enhanced Text Rendering: Improved Chinese/English text rendering and multi-text layout capabilities.
It claims to outperform same-size models in instruction following and editing preservation, while competing with large commercial models in text rendering and composition.
More from Models
- Gemini 4 Argon hits AssemblyAI's LLM Gateway, tops voice bench at 99.5 across 50+ models — AssemblyAI · 2026-10-16
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- 'Opus 5.5' collage demos spark claim: models have taste, no moat — yuwen_lu_ · 2026-10-16
- PrismML ships Bonsai 2 ternary models: 9B fits in 2GB for local AI — gajesh · 2026-10-16
- Apple MLX Runs 816B Muse Spark Open at 36+ Tokens/s on Four Mac Studios — andrejusb · 2026-10-16
- vLLM Ships Day-0 Support for Meta's 816B Open-Weight Muse Spark Open — woosuk_k · 2026-10-16