SenseTime open-sources SenseNova U1.5 Lite: 8B unified model with native 4K generation
HeyNayeem · x · 2026-08-26
SenseTime has open-sourced SenseNova U1.5 Lite (5.6k GitHub stars, includes ComfyUI integration and training code). It's a lightweight 8B unified multimodal model covering visual understanding, generation and editing:
- Native 2K/4K high-resolution output with better detail, composition and realism
- Improved complex instruction following across subjects, counts, text, layouts and styles
- Enhanced Chinese/English text rendering and multi-text layout for posters, infographics and brand assets
- Precise editing and control via visual markers, bounding boxes and multi-image references
The company claims it outperforms same-size models in instruction following and editing preservation while competing with large commercial models in text rendering.
More from Multimodal
- Open-source LoRA turns MiniMax H3 into seamless 360-degree orbit videos from a single photo — camenduru · 2026-10-15
- Neon Noir Elegance prompt template goes viral with striking pink-blue two-tone outputs — LudovicCreator · 2026-10-15
- Krea 2 Turbo + px16 LoRA generates game-ready pixel art in 5s, where GPT Image 2.5 fails — Angaisb_ · 2026-10-15
- How Goldfish Made Its Kung Fu Scenes: Real Nanquan Choreography + Seedance 2.5 — JunieLauX · 2026-10-15
- Custom px16 LoRA makes Krea 2 Turbo churn out pixel icons at 5s each — Angaisb_ · 2026-10-15
- Prompt share: 'Crimson Footsteps' makes one red element pop in monochrome AI photos — azed_ai · 2026-10-15