Shanghai AI Lab unveils Intern Lumina U2, a diffusion LLM unifying image, video and 3D tasks
Shanghai-AI-Laboratory · hf · 2026-10-16
Shanghai AI Laboratory released Intern Lumina U2, a multi-codebook diffusion language model that unifies visual understanding and generation in a single backbone.
- Uses multi-codebook discrete visual tokens to handle image, video, and 3D — both understanding and generation
- Covers image generation, editing, and image/video/3D QA
- Benchmarks against Show-o2, BAGEL, LLaDA and others on CharXiv, MathVision, MVBench, DFG-Bench, leading on many
- Claims faster inference than comparable unified models
Another serious entrant in the unified understanding-and-generation track.
More from Models
- ChatGPT voice selection breaks after GPT-Live-1.1 rollout on Android — shaunralston · 2026-10-16
- vLLM officially supports Muse Spark Open: multimodal, 1M context, agentic — vllm_project · 2026-10-16
- Liquid AI ships LFM2.5-24B-A2B: 24B MoE with 2B active params for local agents — JosephJacks_ · 2026-10-16
- Cherry pi on a Raspberry Pi: the tiny-model rumor developers are watching — sull · 2026-10-16
- anon-1b: an open-weights Gemma fine-tune trained on 4chan greentext — rickasaurus · 2026-10-16
- Astra 6.1 reportedly delayed while OpenAI's frontier RL stays paused over safety concerns — haider1 · 2026-10-16