Papers › Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

5 Dec 2024CVPR 2025 1arXiv:2412.04431archive 2025-07-28

Jian Han, Jinlai Liu, Yi Jiang, Bin Yan, Yuqi Zhang, Zehuan Yuan, Bingyue Peng, Xiaobing Liu

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction framework with an infinite-vocabulary tokenizer & classifier and bitwise self-correction mechanism, remarkably improving the generation capacity and details. By theoretically scaling the tokenizer vocabulary size to infinity and concurrently scaling the transformer size, our method significantly unleashes powerful scaling capabilities compared to vanilla VAR. Infinity sets a new record for autoregressive text-to-image models, outperforming top-tier diffusion models like SD3-Medium and SDXL. Notably, Infinity surpasses SD3-Medium by improving the GenEval benchmark score from 0.62 to 0.73 and the ImageReward benchmark score from 0.87 to 0.96, achieving a win rate of 66%. Without extra optimization, Infinity generates a high-quality 1024x1024 image in 0.8 seconds, making it 2.6x faster than SD3-Medium and establishing it as the fastest text-to-image model. Models and codes will be released to promote further exploration of Infinity for visual generation and unified tokenizer modeling.

PaperPDFConference PDFCodeCode 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="2412.04431")

Code

Syntology Ran 12 of 19 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · violated contract; 5 ran · our draft was wrong; 4 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 12 samples from 1 repository, 5 ran; 4 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

FoundationVision/Infinity officialmentioned on GitHubpytorch report
FoundationVision/VAR mentioned on GitHubpytorchMIT 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

19 samples harvested; 12 ran; 0 honoured the contract we drafted; 7 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.

1ran · violated contract
5ran · our draft was wrong
4ran · fixture could not drive it
2ran
7unverified

Licence: 4 of the 19 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

aug_with_positive_prompt FoundationVision/Infinity/tools/run_infinity.py official repository ran · violated contract fingerprinted MIT (permissive) · 9e7e8cb16293d38e · report
encode_prompt FoundationVision/Infinity/tools/run_infinity.py official repository ran · fixture could not drive it MIT (permissive) · c490ce79bba70918 · report
extract_key_val FoundationVision/Infinity/tools/run_infinity.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 8535a42ccd56fce0 · report
Normalize FoundationVision/VAR/models/basic_vae.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report
drop_path FoundationVision/VAR/models/helpers.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 971ae8d2d8313e30 · report
gumbel_softmax_with_rng FoundationVision/VAR/models/helpers.py community (archive-listed) ran MIT (permissive) · e543491ea064c733 · report
nonlinearity FoundationVision/VAR/models/basic_vae.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report
sample_with_top_k_top_p_ FoundationVision/VAR/models/helpers.py community (archive-listed) ran MIT (permissive) · 80371584448f2f6e · report
allgather FoundationVision/VAR/dist.py community (archive-listed) unverified MIT (permissive) · e847ee15f089dee6 · report
allreduce FoundationVision/VAR/dist.py community (archive-listed) unverified MIT (permissive) · ff4c548fd07140d0 · report
build_dataset FoundationVision/VAR/utils/data.py community (archive-listed) unverified MIT (permissive) · 8ff7703f731423de · report
make_attn FoundationVision/VAR/models/basic_vae.py community (archive-listed) unverified MIT (permissive) · 793c7e2489dd8dfc · report
new_group FoundationVision/VAR/dist.py community (archive-listed) unverified MIT (permissive) · 826ea3fc406a6a09 · report
normalize_01_into_pm1 FoundationVision/VAR/utils/data.py community (archive-listed) unverified MIT (permissive) · eabecb1bb23906fe · report
pil_loader FoundationVision/VAR/utils/data.py community (archive-listed) unverified MIT (permissive) · b1714d4e3b7ac3b9 · report
get_params_num identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 6a19741de3a68058 · report
sample_with_top_k_top_p_also_inplace_modifying_logits_ identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 9526ce09c7148703 · report
sampling_with_top_k_top_p_also_inplace_modifying_probs_ identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 5451c3f14c7e520c · report
timed identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 844a4aecea80d106 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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