Papers › Conditional Image Generation with PixelCNN Decoders

Conditional Image Generation with PixelCNN Decoders

16 Jun 2016NeurIPS 2016 12arXiv:1606.05328archive 2025-07-28

Aaron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, Koray Kavukcuoglu

This work explores conditional image generation with a new image density model based on the PixelCNN architecture. The model can be conditioned on any vector, including descriptive labels or tags, or latent embeddings created by other networks. When conditioned on class labels from the ImageNet database, the model is able to generate diverse, realistic scenes representing distinct animals, objects, landscapes and structures. When conditioned on an embedding produced by a convolutional network given a single image of an unseen face, it generates a variety of new portraits of the same person with different facial expressions, poses and lighting conditions. We also show that conditional PixelCNN can serve as a powerful decoder in an image autoencoder. Additionally, the gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.

PaperPDFConference PDFCodeCode Syntology ran

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 14 code samples harvested from 5 repositories linked to this paper: 8 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; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 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: community (archive-listed): 14 samples from 5 repositories, 8 ran (6 with no instrument failure; 2 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 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

14 repositories listed; official and paper-mentioned ones first.

PsorTheDoctor/microarray-data mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Regularization of Convolutional Neural Networks with Cutout (arXiv:1708.04552; that paper's own run record: 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified), mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified) and CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
SJHNJU/Gated_PixelCNN mentioned on GitHubtfSyntology: not harvested report
SJHNJU/gated-pixelcnn mentioned on GitHubtfSyntology: not harvested report
anordertoreclaim/PixelCNN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pixel Recurrent Neural Networks (arXiv:1601.06759; that paper's own run record: 19 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
chandlersupple/Tensorflow-PixelCNN mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
eyalbetzalel/pytorch-generative mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
eyalbetzalel/pytorch-generative-v2 mentioned on GitHubpytorchMITSyntology: not harvested report
kamenbliznashki/pixel_models mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
kkleidal/gatedpixelcnnpytorch mentioned on GitHubpytorchMITSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
openai/pixel-cnn mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
rampage644/wavenet mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to WaveNet: A Generative Model for Raw Audio (arXiv:1609.03499; that paper's own run record: 65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified); nothing checks that they implement this paper's method. report
vocong25/gated_pixelcnn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pixel Recurrent Neural Networks (arXiv:1601.06759; that paper's own run record: 19 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
EugenHotaj/pytorch-generative pytorchSyntology: 2 samples, 0 ran · 2 unverified report
sarus-tech/tf2-published-models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Auto-Encoding Variational Bayes (arXiv:1312.6114; that paper's own run record: 140 ran (of which 52 constructed an object rather than computing a result; 120 with no instrument failure: 4 honoured, 2 violated, 114 with no contract checked; 20 where Syntology's instrument failed) · 59 unverified), Pixel Recurrent Neural Networks (arXiv:1601.06759; that paper's own run record: 19 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified) and Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. 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.

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

14 samples harvested: 8 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; 2 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
4ran
6unverified

Licence: 3 of the 14 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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

chandlersupple/Tensorflow-PixelCNN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mask in 19 papers pixelcnn.py ran · our draft was wrong MIT (permissive) · 1e14e324863c2ccd · report fixture: signature mask_type:str/0/str, num_inputs:int/0/int, num_outputs:int/0/int, kernel_size:tuple/1/int, num_channels:int/0/int · returned ndarray · level recorded 2026-09-22
eyalbetzalel/pytorch-generative community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
animate in 6 papers pytorch_generative/colab_utils.py ran MIT (permissive) · 7486d39d659887c7 · report fixture: signature frames:list/1/Tensor, figsize:tuple/1/int, fps:int/0/int · returned FuncAnimation · level recorded 2026-09-26
compute_receptive_field pytorch_generative/debug.py ran MIT (permissive) · 54d26252e3d6b564 · report fixture: signature model:callable/0/?, img_size:tuple/1/int · returned Tensor · level recorded 2026-09-26
image_positional_encoding pytorch_generative/nn.py ran MIT (permissive) · 97ff1e90a6a32884 · report fixture: signature shape:tuple/1/int · returned Tensor · level recorded 2026-09-26
load_image in 273 papers pytorch_generative/colab_utils.py ran MIT (permissive) · 6e93d4d24f711246 · report fixture: signature path:str/0/str, size:NoneType/0/?, remove_alpha_channel:bool/0/bool · returned Tensor · level recorded 2026-09-26
kamenbliznashki/pixel_models community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
loss_fn in 55 papers
census: 8 implementations from 9 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
pixelcnn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · bd3e6d44a59d468d · report fixture: signature logits:Tensor/5/float, targets:Tensor/4/int · returned Tensor · level recorded 2026-09-22
pixelcnn_gate pixelcnn.py ran · honoured contract fingerprinted no licence file found · pointer only · 68cdfbf37a172d13 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
generate_fn pixelcnn.py unverified no licence file found · pointer only · a88f8690106036a3 · report
kkleidal/gatedpixelcnnpytorch community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
same_padding in 10 papers models/components/pixelcnn.py ran · honoured contract fingerprinted MIT (permissive) · b2d883de2fd93619 · report fixture: signature kernel_size:int/0/int · returned int · level recorded 2026-09-22
negative_log_likelihood in 6 papers mnist_pixelcnn_train.py unverified MIT (permissive) · e1fa075299151e23 · report
quantisize mnist_pixelcnn_train.py unverified MIT (permissive) · 1c783a15bde67d51 · report
EugenHotaj/pytorch-generative community (archive-listed) 2 samples, 0 ran · 2 unverified
reproduce in 6 papers pytorch_generative/models/autoregressive/gated_pixel_cnn.py unverified MIT (permissive) · f5e294f7c52471d8 · report
reproduce in 6 papers pytorch_generative/models/autoregressive/pixel_cnn.py unverified MIT (permissive) · 1eef18f20b4c3e7d · report

Tasks

Conditional Image GenerationDecoderDensity EstimationDescriptiveImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation CIFAR-10 Pixel CNN NLL (bits/dim) 3.03 #10 of 15 Archive leaderboard report
Image Generation ImageNet 32x32 Gated PixelCNN bpd 3.83 #25 of 35 Archive leaderboard report
Image Generation ImageNet 64x64 Gated PixelCNN (van den Oord et al., [2016c]) Bits per dim 3.57 #50 of 65 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

LSTMMasked ConvolutionPixelCNNPixelRNNSigmoid ActivationTanh Activation

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