Shanghai AI Lab releases InternLumina-U2: 16B-A1B multi-codebook diffusion unified multimodal model
Original title:InternLM/InternLumina-U2
AI summary
Shanghai AI Lab has released InternLumina-U2, a 16B-parameter (1B activated) MoE diffusion language model that uses an 8-codebook fully discrete visual representation to uniformly cover text question answering, text-to-image generation, image understanding and editing, and video and 3D understanding.
Key Takeaways
- Shanghai AI Lab has released InternLumina-U2
- a 16B-parameter (1B activated) MoE diffusion language model that uses an 8-codebook fully discrete…
- text-to-image generation,image understanding and editing,and video and 3D understanding.
Quick Facts
- Published
- Updated
- Source
- 上海人工智能实验室 InternLM:原创项目
- Category
- Model Releases
- AI score
- 63
原文给出多码本全离散统一架构的设计细节、基准分数和双硬件适配说明,读者可以了解统一理解与生成模型的一条新路线。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Shanghai AI Lab releases InternLumina-U2: 16B-A1B multi-codebook diffusion unified multimodal model. September 1, 2026. https://new.nat6.net/en/news/cmtym6nge0003ro3hkwsh5vju/