---
format: "aidr-story-markdown/v1"
id: "1b5e04430747b59eb38ec6598b99f73c82b5e3f695359325cdc5bcdbb954ffe3"
canonical_url: "https://aidr.today/1b5e0443?lang=en"
title: "Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-16T00:00:00.000Z"
category: "Models"
topics: ["llm"]
source_urls: ["https://huggingface.co/papers/2610.20818"]
summary: "Intern Lumina U2 is presented as the first diffusion language model to represent multi-codebook visual tokens in a fully discrete space. Each visual position is represented by a group of codes from complementary codebooks, increasing representational capacity while preserving compatibility with discrete text modeling."
---

# Intern Lumina U2: A Multi\-Codebook Diffusion Large Language Model for Omni\-Visual Understanding and Image Generation

> [Open the canonical story](<https://aidr.today/1b5e0443?lang=en>)

**Published:** 2026-10-16T00:00:00.000Z
**Category:** Models
**Topics:** llm

## Summary

Intern Lumina U2 is presented as the first diffusion language model to represent multi\-codebook visual tokens in a fully discrete space\. Each visual position is represented by a group of codes from complementary codebooks, increasing representational capacity while preserving compatibility with discrete text modeling\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.20818>)