SenseNova-U1.5: an 8B encoder-free native unified multimodal model for understanding and generation
Haiwen Diao · hf · 2026-09-11
SenseNova-U1.5 is an 8B native unified multimodal model that performs visual understanding, reasoning, and generation without encoders or VAEs. It combines patch reconstruction, curated data, expert optimization, and on-policy distillation to achieve high fidelity and strong instruction following. Weights are on Hugging Face.
More from Multimodal
- I tested 11 video upscaling methods for AI video: local, Topaz and cloud compared — lopas99 · 2026-10-28
- AI Horde adds Moss-Image for free, no-account image generation on volunteer GPUs — Wanabeelee2 · 2026-10-28
- AI band Techhalla reimagines Slipknot's 'Wait and Bleed' as a 1971 soul performance — Mother-Pear-2392 · 2026-10-28
- Inside the Hailuo H3 Max retro-MV workflow: 15-second chunks, one reference image, multi-shot prompts — techhalla · 2026-10-28
- Open-source pipeline turns Seedance AI video into real PBR textures on your 3D mesh — OdinLovis · 2026-10-28
- AI-generated cyberpunk short 'VHS Sirens' shows off consistent characters and neon city detail — brythehuman · 2026-10-28