Tasks and inputs
InternLumina-U2 is listed for Any-to-any, Image-text-to-text, Text-to-image. It accepts text, image, video and produces text, image. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Nov 19, 2026
InternLumina-U2 is Shanghai AI Lab's masked-diffusion MoE that understands images, video and 3D and generates and edits images with 8-codebook visual tokens.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Pricing conditions: Open weights under Apache 2.0; no hosted price.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Unified models usually split the work: discrete tokens for text, continuous latents for images, and two training objectives that pull against each other. InternLumina-U2, Shanghai AI Laboratory's "Intern Lumina U2", keeps everything discrete. Each visual position is described by codes from eight complementary codebooks, and a masked diffusion language model handles text and images in one space.
The payoff is breadth. One backbone does text QA, text-to-image, image understanding, instruction-based editing, video understanding and 3D understanding.
Shanghai AI Lab rounds it to a 16B-A1B model in one place and gives 16.9B total with about 1.4B active in another, alongside a full architecture breakdown. Use the more precise figures for capacity planning.
| Component | Detail |
|---|---|
| Repository | internlm/InternLumina-U2 (nvidia/ and ascend/ subfolders) |
| Backbone | LLaDA2.0-mini masked diffusion MoE |
| Layers | 20 (1 dense, 19 MoE) |
| Experts | 256 routed + 1 shared, 8 active |
| Visual tokens | AToken, 8 codebooks per position |
| Inputs | text, image, video, 3D |
| Outputs | text, image |
| Licence | Apache 2.0 |
At the input, the eight per-codebook embeddings for a position are concatenated and projected into one backbone token, so sequence length does not grow eightfold. At the output, the diffusion backbone denoises many masked positions in parallel while a small autoregressive head predicts each position's eight codes in order. An optional, training-free sampler called PHV speeds image generation by 4.45x, per the authors.
Checkpoints exist for both Huawei Ascend and NVIDIA hardware. The GitHub repository ships the NVIDIA path, plus SFT training code.
Generation and chart reading are the strong suits. General knowledge (MMMU) is modest, which fits a backbone with roughly a billion and a half active parameters.
Inference code arrived in August and the repository on 1 September 2026, weights followed in October, and the full report is dated 14 October. Check which revision you pull.
It is worth a look if you want one small-active-parameter model for both chart understanding and image generation. Generate fifty images from your own prompt set and run fifty chart questions from your documents through it; compare the images with a dedicated generator such as Seedream 5.0 Flash and the charts with SenseNova-U1.5-8B-MoT. Similar models are listed under any-to-any.
Compare the model on the work you need to complete.
InternLumina-U2 is listed for Any-to-any, Image-text-to-text, Text-to-image. It accepts text, image, video and produces text, image. Use the publisher’s input format and preprocessing for your chosen deployment.
Choose the output size and quality your design needs. Include drafts and revisions when budgeting an accepted image.
The weights are downloadable under Apache-2.0. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Liquid AI
LFM3-Omni-2B is Liquid AI's open any-to-any model: image, video, audio and text in; text and speech out, with multimodal tool calls on-device.
NVIDIA
NLD-Uni (Nemotron-Labs-Diffusion-Uni-8B) is NVIDIA's open diffusion-language model that both understands images and generates them, for research.
NVIDIA
PixelUMM is NVIDIA's encoder-free 15B unified model that understands and generates text, images and video directly in pixel space. Non-commercial.
sensetime
SenseNova-U1.5-8B-MoT is SenseTime's open unified model for native 4K image generation and instruction-based image editing, Apache-2.0 licensed.
Tencent
Hy-Embodied-RxBrain-1.0 is Tencent's 6.2B embodied model that reasons in text and imagines goal images, for planning, world-state prediction and video QA.
google/gemma-4-E2B-it is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.