Papers › Variational Diffusion Models

Variational Diffusion Models

1 Jul 2021arXiv:2107.00630archive 2025-07-28

Diederik P. Kingma, Tim Salimans, Ben Poole, Jonathan Ho

Diffusion-based generative models have demonstrated a capacity for perceptually impressive synthesis, but can they also be great likelihood-based models? We answer this in the affirmative, and introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on standard image density estimation benchmarks. Unlike other diffusion-based models, our method allows for efficient optimization of the noise schedule jointly with the rest of the model. We show that the variational lower bound (VLB) simplifies to a remarkably short expression in terms of the signal-to-noise ratio of the diffused data, thereby improving our theoretical understanding of this model class. Using this insight, we prove an equivalence between several models proposed in the literature. In addition, we show that the continuous-time VLB is invariant to the noise schedule, except for the signal-to-noise ratio at its endpoints. This enables us to learn a noise schedule that minimizes the variance of the resulting VLB estimator, leading to faster optimization. Combining these advances with architectural improvements, we obtain state-of-the-art likelihoods on image density estimation benchmarks, outperforming autoregressive models that have dominated these benchmarks for many years, with often significantly faster optimization. In addition, we show how to use the model as part of a bits-back compression scheme, and demonstrate lossless compression rates close to the theoretical optimum. Code is available at https://github.com/google-research/vdm .

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 38 code samples harvested from 6 repositories linked to this paper: 29 ran (of which 18 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 1 violated, 19 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 20 samples from 4 repositories, 16 ran (12 with no instrument failure; 4 where Syntology's instrument failed); found in paper text by Syntology: 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/vdm officialmentioned in papermentioned on GitHubjaxSyntology: 16 samples, 11 ran (4 instrument-failed) · 5 unverified report
addtt/variational-diffusion-models mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (3 instrument-failed) · 1 unverified report
martenlienen/bsi mentioned on GitHubjaxSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
revsic/jax-variational-diffwave mentioned on GitHubjaxSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
yoyololicon/variational-diffwave mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 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

38 samples harvested: 29 ran (of which 18 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 1 violated, 19 with no contract checked; 9 where Syntology's instrument failed) · 9 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.

1ran · violated contract
6ran · our draft was wrong
3ran; the contract check could not run
19ran
9unverified

Licence: 2 of the 38 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 6 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”. For 2 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.

google-research/vdm official repository 16 samples, 11 ran (4 instrument-failed) · 5 unverified
AttnBlock in 22 papers model_vdm.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 561db3edf2a73d49 · report fixture: returned AttnBlock · level recorded 2026-09-22
Base2FourierFeatures model_vdm.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1fd721cbc30c55b2 · report fixture: returned Base2FourierFeatures · level recorded 2026-09-22
EncDec model_vdm.py ran Apache-2.0 (permissive) · 491caa588adc4c8f · report fixture: returned EncDec · level recorded 2026-09-22
NoiseSchedule_FixedLinear model_vdm.py ran Apache-2.0 (permissive) · 069d8acfc9e74bee · report fixture: returned NoiseSchedule_FixedLinear · level recorded 2026-09-22
NoiseSchedule_Scalar model_vdm.py ran Apache-2.0 (permissive) · 529196025d205b76 · report fixture: returned NoiseSchedule_Scalar · level recorded 2026-09-22
VDMConfig model_vdm.py ran Apache-2.0 (permissive) · f447b1a658e14845 · report fixture: returned VDMConfig · level recorded 2026-09-22
VDMOutput model_vdm.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a08f56d5383b4deb · report fixture: returned VDMOutput · level recorded 2026-09-22
_invert_perm model_vdm.py ran · our draft was wrong Apache-2.0 (permissive) · 6f2b76f02949e8a2 · report fixture: signature perm:list/1/int · returned tuple · level recorded 2026-09-22
constant_init in 10 papers model_vdm.py ran · our draft was wrong Apache-2.0 (permissive) · efd5fbe71f5d4417 · report fixture: signature value:float/0/float, dtype:str/0/str · returned function · level recorded 2026-09-22
dot_product_attention in 15 papers model_vdm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 3650a2dfe2e97298 · report fixture: signature query:ArrayImpl/4/float, key:ArrayImpl/4/float, value:ArrayImpl/4/float, dtype:callable/0/?, bias:NoneType/0/?, axis:tuple/1/int, precision:NoneType/0/? · returned ArrayImpl · level recorded 2026-09-22
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
model_vdm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 0a5352fc3e23401b · report fixture: signature timesteps:ArrayImpl/1/float, embedding_dim:int/0/int, dtype:callable/0/? · returned ArrayImpl · level recorded 2026-09-22
DenseMonotone model_vdm.py unverified Apache-2.0 (permissive) · 2bfdfec42cfdcdcf · report
NoiseSchedule_NNet model_vdm.py unverified Apache-2.0 (permissive) · 6f9deb29cfceeb7f · report
ResnetBlock in 49 papers model_vdm.py unverified Apache-2.0 (permissive) · 32c40355362a0b32 · report
ScoreUNet model_vdm.py unverified Apache-2.0 (permissive) · 3c07ccd2fae8c079 · report
VDM model_vdm.py unverified Apache-2.0 (permissive) · 29cb7af455c82dc4 · report
addtt/variational-diffusion-models community (archive-listed) 6 samples, 5 ran (3 instrument-failed) · 1 unverified
FixedLinearSchedule vdm.py ran fingerprinted MIT (permissive) · d212b472730598ed · report fixture: returned FixedLinearSchedule · level recorded 2026-09-22
LearnedLinearSchedule vdm.py ran fingerprinted MIT (permissive) · ea5520290d73f53d · report fixture: returned LearnedLinearSchedule · level recorded 2026-09-22
kl_std_normal vdm.py ran · our draft was wrong fingerprinted MIT (permissive) · abd7e936a4a2330d · report fixture: signature mean_squared:Tensor/2/float, var:Tensor/2/float · returned Tensor · level recorded 2026-09-22
maybe_unpack_batch vdm.py ran · our draft was wrong fingerprinted MIT (permissive) · 656e283a7a532e0d · report fixture: signature batch:Tensor/2/float · returned tuple · level recorded 2026-09-22
unsqueeze_right vdm.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 9081710b06dc58b5 · report fixture: signature x:Tensor/2/float, num_dims:int/0/int · returned Tensor · level recorded 2026-09-22
VDM vdm.py unverified MIT (permissive) · d69b5df2d07b253c · report
martenlienen/bsi community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Discretization bsi/vdm.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · bb89d1300208329a · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22
broadcast_right bsi/vdm.py ran · violated contract fingerprinted MIT (permissive) · 5c967875cb5a67f1 · report fixture: signature x:Tensor/2/float, other:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VDM bsi/vdm.py unverified MIT (permissive) · b780d07f50dbb622 · report
revsic/jax-variational-diffwave community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
Config in 46 papers vlbdiffwave/impl.py ran MIT (permissive) · 59e0526c50f31501 · report fixture: returned Config · level recorded 2026-09-22
LogSNR vlbdiffwave/impl.py ran · metamorphic tier: deterministic MIT (permissive) · 212e87de38149204 · report fixture: returned LogSNR · level recorded 2026-09-22
PosDense vlbdiffwave/impl.py ran · metamorphic tier: deterministic MIT (permissive) · cb2f69aa1655d268 · report fixture: returned PosDense · level recorded 2026-09-22
WNDense vlbdiffwave/impl.py ran · metamorphic tier: deterministic MIT (permissive) · 3421a6b0be94af74 · report fixture: returned WNDense · level recorded 2026-09-22
WNDilatedConv vlbdiffwave/impl.py ran · metamorphic tier: deterministic MIT (permissive) · a4d6fbb9fe89feb5 · report fixture: returned WNDilatedConv · level recorded 2026-09-22
WaveNetBlock vlbdiffwave/impl.py ran MIT (permissive) · f55545fd60b5575f · report fixture: returned WaveNetBlock · level recorded 2026-09-22
constant in 36 papers vlbdiffwave/impl.py ran · our draft was wrong MIT (permissive) · 4f4db12a92cab549 · report fixture: signature value:float/0/float · returned function · level recorded 2026-09-22
DiffWave in 5 papers vlbdiffwave/impl.py unverified MIT (permissive) · dacd58542a91f9cc · report
VLBDiffWave vlbdiffwave/impl.py unverified MIT (permissive) · 9f2532a370c4d0c4 · report
yoyololicon/variational-diffwave community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DiffWave in 5 papers src/diffwave/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · ae2c486b1f90a559 · report fixture: returned DiffWave · level recorded 2026-09-22
ResidualBlock in 100 papers src/diffwave/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7fcce4b4613629ad · report fixture: returned ResidualBlock · level recorded 2026-09-22
hojonathanho/diffusion found in paper text by Syntology 2 samples, 2 ran (1 instrument-failed) · 0 unverified
GaussianDiffusion2 diffusion_tf/diffusion_utils_2.py ran no licence file found · pointer only · 16c2edc6a8669837 · report fixture: returned GaussianDiffusion2 · level recorded 2026-09-22
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input
diffusion_tf/diffusion_utils_2.py ran · our draft was wrong no licence file found · pointer only · 5f5e07eb94d1c5d2 · report fixture: signature mean1:SymbolicTensor/2/float, logvar1:SymbolicTensor/2/float, mean2:SymbolicTensor/2/float, logvar2:SymbolicTensor/2/float · returned SymbolicTensor · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

6 sibling assemblies for Variational Diffusion Models (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 9 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. VLBDiffWave entry · level 0 · unverified · 9f2532a370c4d0c4
  2. Config helper · level 1 · ran · 59e0526c50f31501
  3. DiffWave model · level 0 · unverified · dacd58542a91f9cc
  4. LogSNR scheduler · level 1 · ran · 212e87de38149204
  5. WaveNetBlock model · level 1 · ran · f55545fd60b5575f
  6. PosDense helper · level 1 · ran · cb2f69aa1655d268
  7. constant helper · level 1 · ran · our draft was wrong · 4f4db12a92cab549
  8. WNDense helper · level 1 · ran · 3421a6b0be94af74
  9. WNDilatedConv helper · level 1 · ran · a4d6fbb9fe89feb5

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. DiffWave entry · level 1 · ran · ae2c486b1f90a559
  2. Conv1d helper · level 1 · ran · our draft was wrong · 2109126c17b0f297
  3. DiffusionEmbedding model · level 1 · ran · 4774d75a47fa7f01
  4. ResidualBlock model · level 1 · ran · 7fcce4b4613629ad
  5. SpectrogramUpsampler model · level 1 · ran · e3b3ff81ba235015
  6. silu helper · level 1 · ran · honoured contract · d9caeeced554450f

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 16 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. VDM entry · level 0 · unverified · 29cb7af455c82dc4
  2. EncDec model · level 1 · ran · 491caa588adc4c8f
  3. NoiseSchedule_FixedLinear scheduler · level 1 · ran · 069d8acfc9e74bee
  4. NoiseSchedule_NNet scheduler · level 0 · unverified · 6f9deb29cfceeb7f
  5. NoiseSchedule_Scalar scheduler · level 1 · ran · 529196025d205b76
  6. ScoreUNet model · level 0 · unverified · 3c07ccd2fae8c079
  7. VDMConfig helper · level 1 · ran · f447b1a658e14845
  8. VDMOutput helper · level 1 · ran · a08f56d5383b4deb
  9. DenseMonotone helper · level 0 · unverified · 2bfdfec42cfdcdcf
  10. constant_init helper · level 1 · ran · our draft was wrong · efd5fbe71f5d4417
  11. AttnBlock model · level 1 · ran · 561db3edf2a73d49
  12. Base2FourierFeatures helper · level 1 · ran · 1fd721cbc30c55b2
  13. ResnetBlock model · level 0 · unverified · 32c40355362a0b32
  14. get_timestep_embedding helper · level 1 · ran; the contract check could not run (RAISES) · 0a5352fc3e23401b
  15. dot_product_attention helper · level 1 · ran; the contract check could not run (RAISES) · 3650a2dfe2e97298
  16. _invert_perm helper · level 1 · ran · our draft was wrong · 6f2b76f02949e8a2

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 6 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. VDM entry · level 0 · unverified · d69b5df2d07b253c
  2. FixedLinearSchedule scheduler · level 1 · ran · d212b472730598ed
  3. LearnedLinearSchedule scheduler · level 1 · ran · ea5520290d73f53d
  4. kl_std_normal loss · level 1 · ran · our draft was wrong · abd7e936a4a2330d
  5. maybe_unpack_batch helper · level 1 · ran · our draft was wrong · 656e283a7a532e0d
  6. unsqueeze_right helper · level 1 · ran; the contract check could not run (RAISES) · 9081710b06dc58b5

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. GaussianDiffusion2 entry · level 1 · ran · 16c2edc6a8669837
  2. normal_kl loss · level 1 · ran · our draft was wrong · 5f5e07eb94d1c5d2

harvested Assembly for Variational Diffusion Models (graph method: Variational Diffusion Models). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. VDM entry · level 0 · unverified · b780d07f50dbb622
  2. Discretization helper · level 1 · ran · bb89d1300208329a
  3. broadcast_right helper · level 1 · ran · violated contract · 5c967875cb5a67f1

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="2107.00630") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Density EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation CIFAR-10 VDM NLL (bits/dim) 2.65 #4 of 15 Archive leaderboard report
Density Estimation ImageNet 32x32 VDM NLL (bits/dim) 3.72 #3 of 5 Archive leaderboard report
Image Generation ImageNet 32x32 VDM bpd 3.72 #17 of 35 Archive leaderboard report
Image Generation ImageNet 64x64 VDM Bits per dim 3.40 #40 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.

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