Papers › Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, Zehuan Yuan
We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly. We reexamine design spaces of image tokenizers, scalability properties of image generation models, and their training data quality. The outcome of this exploration consists of: (1) An image tokenizer with downsample ratio of 16, reconstruction quality of 0.94 rFID and codebook usage of 97% on ImageNet benchmark. (2) A series of class-conditional image generation models ranging from 111M to 3.1B parameters, achieving 2.18 FID on ImageNet 256x256 benchmarks, outperforming the popular diffusion models such as LDM, DiT. (3) A text-conditional image generation model with 775M parameters, from two-stage training on LAION-COCO and high aesthetics quality images, demonstrating competitive performance of visual quality and text alignment. (4) We verify the effectiveness of LLM serving frameworks in optimizing the inference speed of image generation models and achieve 326% - 414% speedup. We release all models and codes to facilitate open-source community of visual generation and multimodal foundation models.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2406.06525")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2406.06525", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2406.06525")
Code
Syntology 15 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 15 samples from 1 repository, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- 0606zt/panollama, community (archive-listed): harvested for 2 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 9 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from foundationvision/llamagen. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
5cceaa9d0edbce06 · report
fixture: signature args:Args/0/?, transform:callable/0/? · returned ImageFolder · level recorded 2026-09-25 b6635606f35f6a1a · report
fixture: signature args:Namespace/0/? · returned CustomDataset · level recorded 2026-09-25 02cb09299c18ee5d · report
fixture: signature args:Args/0/?, transform:callable/0/? · returned Text2ImgDataset · level recorded 2026-09-24 ff9ed4675cb307aa · report
fixture: signature args:Args/0/? · returned Text2ImgDatasetCode · level recorded 2026-09-24 090d7b6b1260114e · report
fixture: signature args:Args/0/?, transform:callable/0/? · returned Text2ImgDatasetImg · level recorded 2026-09-24 1712a07966b542ee · report
fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned Image · level recorded, date not recorded f6ff7671338c9c92 · report
fixture: signature n:int/0/int, k:int/0/int · returned int · level recorded 2026-09-22 7f53b2cdcd16fad9 · report
fixture: signature grid_size:int/0/int, n_elem:int/0/int, base:int/0/int, cls_token_num:int/0/int · returned Tensor · level recorded 2026-09-22 census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket autoregressive/models/generate.py ran MIT (permissive) here; the stored copy is pointer only ·
de8908ac0f302419 · report
fixture: signature logits:Tensor/3/float, temperature:float/0/float, top_k:int/0/int, top_p:float/0/float, sample_logits:bool/0/bool · returned tuple · level recorded 2026-09-25 census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket autoregressive/models/generate.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only ·
f2fea48028c7ae80 · report
fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-25 a5dc3fcd09ebc843 · report
0a65aaf586d4f90b · report
9dac59261197935f · report
0f0ff4e443413018 · report
980fb099f82d8b84 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | ImageNet 256x256 | LlamaGen | FID | 2.18 | #53 of 94 | Archive leaderboard | report |
| Image Reconstruction | Ultra-High Resolution Image Reconstruction Benchmark | LlamaGen (16x16) | LPIPS | 0.177 | #4 of 6 | Archive leaderboard | report |
| Image Reconstruction | Ultra-High Resolution Image Reconstruction Benchmark | LlamaGen (16x16) | PSNR | 23.90 | #4 of 6 | Archive leaderboard | report |
| Image Reconstruction | Ultra-High Resolution Image Reconstruction Benchmark | LlamaGen (16x16) | SSIM | 0.720 | #4 of 6 | Archive leaderboard | report |
| Image Reconstruction | Ultra-High Resolution Image Reconstruction Benchmark | LlamaGen (16x16) | rFID | 5.59 | #4 of 6 | 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.
Methods
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