Papers › Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

27 Mar 2025arXiv:2503.21758archive 2025-07-28

Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, Xiangyang Zhu, Manyuan Zhang, Will Beddow, Erwann Millon, Victor Perez, Wenhai Wang, Conghui He, Bo Zhang, Xiaohong Liu, Hongsheng Li, Yu Qiao, Chang Xu, Peng Gao

We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a unified architecture (Unified Next-DiT) that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and allowing seamless task expansion. Besides, since high-quality captioners can provide semantically well-aligned text-image training pairs, we introduce a unified captioning system, Unified Captioner (UniCap), specifically designed for T2I generation tasks. UniCap excels at generating comprehensive and accurate captions, accelerating convergence and enhancing prompt adherence. (2) Efficiency - to improve the efficiency of our proposed model, we develop multi-stage progressive training strategies and introduce inference acceleration techniques without compromising image quality. Extensive evaluations on academic benchmarks and public text-to-image arenas show that Lumina-Image 2.0 delivers strong performances even with only 2.6B parameters, highlighting its scalability and design efficiency. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-Image-2.0.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2503.21758")

Code

Syntology Ran 7 of 16 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alpha-vllm/lumina-image-2.0 officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 7 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
3ran
9unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Alpha-VLLM/Lumina-Image-2.0. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

interpolate_fn Alpha-VLLM/Lumina-Image-2.0/transport/dpm_solver.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6a35b62fbc80f70a · report
center_crop_arr Alpha-VLLM/Lumina-Image-2.0/imgproc.py official repository ran · our draft was wrong Apache-2.0 (permissive) · ea73360d2d5d9224 · report
expand_dims Alpha-VLLM/Lumina-Image-2.0/transport/dpm_solver.py official repository ran · our draft was wrong Apache-2.0 (permissive) · e6110366588c5c65 · report
expand_t_like_x Alpha-VLLM/Lumina-Image-2.0/transport/path.py official repository ran Apache-2.0 (permissive) · 1c00a422b396fa8b · report
log_state Alpha-VLLM/Lumina-Image-2.0/transport/utils.py official repository ran Apache-2.0 (permissive) · e0c9eec71fe93415 · report
mean_flat Alpha-VLLM/Lumina-Image-2.0/transport/utils.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b883daa24762cb05 · report
modulate Alpha-VLLM/Lumina-Image-2.0/models/model.py official repository ran fingerprinted Apache-2.0 (permissive) · 128eb60a7316f121 · report
apply_average_pool Alpha-VLLM/Lumina-Image-2.0/finetune.py official repository unverified Apache-2.0 (permissive) · 36a146cad5a4abd0 · report
center_crop Alpha-VLLM/Lumina-Image-2.0/imgproc.py official repository unverified Apache-2.0 (permissive) · 241d401b6c9cb411 · report
dataloader_collate_fn Alpha-VLLM/Lumina-Image-2.0/finetune.py official repository unverified Apache-2.0 (permissive) · 3c0739fc97f1625d · report
encode_prompt Alpha-VLLM/Lumina-Image-2.0/sample.py official repository unverified Apache-2.0 (permissive) · 2efc694c55219099 · report
get_train_sampler Alpha-VLLM/Lumina-Image-2.0/finetune.py official repository unverified Apache-2.0 (permissive) · 7fba42c78fe9f3c3 · report
model_wrapper Alpha-VLLM/Lumina-Image-2.0/transport/dpm_solver.py official repository unverified Apache-2.0 (permissive) · 3b14933b6646c3c6 · report
none_or_str Alpha-VLLM/Lumina-Image-2.0/sample.py official repository unverified Apache-2.0 (permissive) · 2fc6fdb85f13dc41 · report
time_shift Alpha-VLLM/Lumina-Image-2.0/transport/utils.py official repository unverified Apache-2.0 (permissive) · 811faa8400431f27 · report
var_center_crop Alpha-VLLM/Lumina-Image-2.0/imgproc.py official repository unverified Apache-2.0 (permissive) · a14f0d1dfea0492b · report

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation DPG Lumina-Image 2.0 Overall 87.2 #1 of 2 Archive leaderboard report
Text-to-Image Generation GenEval Lumina-Image 2.0 Overall 0.73 #11 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections