Papers › ControlAR: Controllable Image Generation with Autoregressive Models

ControlAR: Controllable Image Generation with Autoregressive Models

3 Oct 2024arXiv:2410.02705archive 2025-07-28

Zongming Li, Tianheng Cheng, Shoufa Chen, Peize Sun, Haocheng Shen, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang

Autoregressive (AR) models have reformulated image generation as next-token prediction, demonstrating remarkable potential and emerging as strong competitors to diffusion models. However, control-to-image generation, akin to ControlNet, remains largely unexplored within AR models. Although a natural approach, inspired by advancements in Large Language Models, is to tokenize control images into tokens and prefill them into the autoregressive model before decoding image tokens, it still falls short in generation quality compared to ControlNet and suffers from inefficiency. To this end, we introduce ControlAR, an efficient and effective framework for integrating spatial controls into autoregressive image generation models. Firstly, we explore control encoding for AR models and propose a lightweight control encoder to transform spatial inputs (e.g., canny edges or depth maps) into control tokens. Then ControlAR exploits the conditional decoding method to generate the next image token conditioned on the per-token fusion between control and image tokens, similar to positional encodings. Compared to prefilling tokens, using conditional decoding significantly strengthens the control capability of AR models but also maintains the model's efficiency. Furthermore, the proposed ControlAR surprisingly empowers AR models with arbitrary-resolution image generation via conditional decoding and specific controls. Extensive experiments can demonstrate the controllability of the proposed ControlAR for the autoregressive control-to-image generation across diverse inputs, including edges, depths, and segmentation masks. Furthermore, both quantitative and qualitative results indicate that ControlAR surpasses previous state-of-the-art controllable diffusion models, e.g., ControlNet++. Code, models, and demo will soon be available at https://github.com/hustvl/ControlAR.

PaperPDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 24 code samples harvested from 1 repository linked to this paper: 17 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 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: 24 samples from 1 repository, 17 ran (14 with no instrument failure; 3 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.

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.

hustvl/controlar officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 24 samples, 17 ran (3 instrument-failed) · 7 unverified 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

24 samples harvested: 17 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 7 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.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
11ran
7unverified

Licence: 4 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 hustvl/controlar. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

hustvl/controlar official repository 24 samples, 17 ran (3 instrument-failed) · 7 unverified
CaptionEmbedder autoregressive/models/gpt.py ran Apache-2.0 (permissive) · 0a1aa4e4837aba74 · report fixture: returned CaptionEmbedder · level recorded 2026-09-22
ConditionEmbedder autoregressive/models/gpt.py ran Apache-2.0 (permissive) · 28672d2f5d6d75b9 · report fixture: returned ConditionEmbedder · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
autoregressive/models/gpt.py ran fingerprinted Apache-2.0 (permissive) · 76f9e42efc0d4711 · report fixture: returned DropPath · level recorded 2026-09-22
FeedForward in 198 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · cf99c2811308e5e5 · report fixture: returned FeedForward · level recorded 2026-09-22
KVCache in 5 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · 0b441179596bf2b5 · report fixture: returned KVCache · level recorded 2026-09-22
LabelEmbedder in 13 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · 7a710e6cde2ae35c · report fixture: signature labels:Tensor/1/int, train:bool/0/bool, force_drop_ids:NoneType/0/? · returned tuple · level recorded 2026-09-24
MLP in 375 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · eec94bbc10306be0 · report fixture: returned MLP · level recorded 2026-09-22
ModelArgs in 13 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · 9e7e8b336fa1eb12 · report fixture: returned ModelArgs · level recorded 2026-09-22
RMSNorm in 61 papers autoregressive/models/gpt.py ran Apache-2.0 (permissive) · edd6b8543cc0d1ab · report fixture: returned RMSNorm · level recorded 2026-09-22
build_imagenet in 6 papers dataset/imagenet.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 5cceaa9d0edbce06 · report fixture: signature args:Args/0/?, transform:callable/0/? · returned ImageFolder · level recorded 2026-09-25
build_imagenet_code in 6 papers dataset/imagenet.py ran · our draft was wrong Apache-2.0 (permissive) · 489c6f42beab887e · report fixture: signature args:Args/0/? · returned CustomDataset · level recorded 2026-09-24
create_npz_from_sample_folder in 30 papers create_npz.py ran · our draft was wrong Apache-2.0 (permissive) · 432162d12f959985 · report fixture: signature sample_dir:str/0/str, num:int/0/int · returned str · level recorded 2026-09-24
find_multiple in 31 papers autoregressive/models/gpt.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · f6ff7671338c9c92 · report fixture: signature n:int/0/int, k:int/0/int · returned int · level recorded 2026-09-22
get_causal_mask in 6 papers autoregressive/models/gpt.py ran · violated contract Apache-2.0 (permissive) · 8e142bd1a80ed2ff · report fixture: signature seq_length:int/0/int · returned Tensor · level recorded 2026-09-22
precompute_freqs_cis_2d in 13 papers autoregressive/models/gpt.py ran · honoured contract Apache-2.0 (permissive) · 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
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
autoregressive/models/generate.py ran Apache-2.0 (permissive) · 2c1c9c90fbedc5d3 · 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 2026-09-24
top_k_top_p_filtering in 96 papers
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) Apache-2.0 (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
Transformer in 173 papers autoregressive/models/gpt.py unverified Apache-2.0 (permissive) · 152a894d1340f06b · report
TransformerBlock in 73 papers autoregressive/models/gpt.py unverified Apache-2.0 (permissive) · 7baa685224160fe5 · report
ViT_Adapter autoregressive/models/gpt.py unverified Apache-2.0 (permissive) · 7ea7bc571b41dc22 · report
apply_rotary_emb in 121 papers autoregressive/models/gpt.py unverified Apache-2.0 (permissive) · 29173bf6147634f3 · report
logits_to_probs in 18 papers autoregressive/models/generate.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 9dac59261197935f · report
precompute_freqs_cis in 112 papers autoregressive/models/gpt.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 0f0ff4e443413018 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for ControlAR (graph method: ControlAR). 18 bricks; individually on a fixture: 13 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. Transformer entry · level 0 · unverified · 152a894d1340f06b
  2. CaptionEmbedder model · level 1 · ran · 0a1aa4e4837aba74
  3. ConditionEmbedder model · level 1 · ran · 28672d2f5d6d75b9
  4. KVCache helper · level 1 · ran · 0b441179596bf2b5
  5. LabelEmbedder model · level 1 · ran · 7a710e6cde2ae35c
  6. MLP helper · level 1 · ran · eec94bbc10306be0
  7. ModelArgs helper · level 1 · ran · 9e7e8b336fa1eb12
  8. RMSNorm model · level 1 · ran · edd6b8543cc0d1ab
  9. TransformerBlock model · level 0 · unverified · 7baa685224160fe5
  10. ViT_Adapter helper · level 0 · unverified · 7ea7bc571b41dc22
  11. find_multiple helper · level 1 · ran · honoured contract · f6ff7671338c9c92
  12. get_causal_mask helper · level 1 · ran · violated contract · 8e142bd1a80ed2ff
  13. precompute_freqs_cis_2d helper · level 1 · ran · honoured contract · 7f53b2cdcd16fad9
  14. Attention model · level 0 · unverified · 8320019fce428945
  15. DropPath helper · level 1 · ran · 76f9e42efc0d4711
  16. FeedForward model · level 1 · ran · cf99c2811308e5e5
  17. drop_path helper · level 1 · ran; the contract check could not run · 87577b3ff9d32712
  18. apply_rotary_emb helper · level 0 · unverified · 29173bf6147634f3

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2410.02705") returns these assemblies with each brick's role and wiring (how to connect).

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