Papers › D2C: Diffusion-Denoising Models for Few-shot Conditional Generation

D2C: Diffusion-Denoising Models for Few-shot Conditional Generation

12 Jun 2021arXiv:2106.06819archive 2025-07-28

Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire. This paper describes Diffusion-Decoding models with Contrastive representations (D2C), a paradigm for training unconditional variational autoencoders (VAEs) for few-shot conditional image generation. D2C uses a learned diffusion-based prior over the latent representations to improve generation and contrastive self-supervised learning to improve representation quality. D2C can adapt to novel generation tasks conditioned on labels or manipulation constraints, by learning from as few as 100 labeled examples. On conditional generation from new labels, D2C achieves superior performance over state-of-the-art VAEs and diffusion models. On conditional image manipulation, D2C generations are two orders of magnitude faster to produce over StyleGAN2 ones and are preferred by 50% - 60% of the human evaluators in a double-blind study.

PaperPDFCodeCode 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 20 code samples: 19 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 20: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 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: community (archive-listed): 19 samples from 2 repositories, 17 ran (11 with no instrument failure; 6 where Syntology's instrument failed); 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 18 samples that ran have no recorded date.

jiamings/d2c mentioned on GitHubpytorchMITSyntology: 17 samples, 15 ran (4 instrument-failed) · 2 unverified report
jiamings/d2c_pre_release mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
MS-P3/code4 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SLAB: Efficient Transformers with Simplified Linear Attention and Progressive... (arXiv:2405.11582; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 2 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

20 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 2 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 · honoured contract
4ran · our draft was wrong
3ran; the contract check could not run
10ran
2unverified

Licence: 8 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 2 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. 1 sample is listed last, in a group without a repository. “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.

jiamings/d2c community (archive-listed) 17 samples, 15 ran (4 instrument-failed) · 2 unverified
Normalize in 154 papers d2c/diffusion/models/diffusion.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c3a6b977022957cb · report fixture: signature in_channels:int/0/int · returned GroupNorm · level recorded, date not recorded
channel_mask d2c/autoencoder/neural_ar_operations.py ran MIT (permissive) · f68e8891796e9ba0 · report fixture: signature c_in:int/0/int, g_in:int/0/int, c_out:int/0/int, zero_diag:bool/0/bool · returned ndarray · level recorded 2026-09-24
create_conv_mask d2c/autoencoder/neural_ar_operations.py ran MIT (permissive) · d95da35d40ec2186 · report fixture: signature kernel_size:int/0/int, c_in:int/0/int, g_in:int/0/int, c_out:int/0/int, zero_diag:bool/0/bool, mirror:bool/0/bool · returned ndarray · level recorded 2026-09-24
fusion1 d2c/autoencoder/thirdparty/adamax.py ran MIT (permissive) · 3b0641f4cd06c379 · report fixture: returned Tensor · level recorded 2026-09-24
get_skip_connection d2c/autoencoder/neural_operations.py ran MIT (permissive) · 76eacbd7f60e8ade · report fixture: returned Identity · level recorded 2026-09-24
get_stride_for_cell_type d2c/autoencoder/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 417c413f2e89d954 · report fixture: signature cell_type:str/0/str · returned int · 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 this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
d2c/diffusion/models/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · cb49209c125de1b4 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded
logit in 16 papers d2c/autoencoder/neural_operations.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · d42ce56b29f68801 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-24
noise_estimation_loss in 19 papers d2c/diffusion/functions/losses.py ran MIT (permissive) · 36a45cceb1209d2f · report fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
d2c/diffusion/models/diffusion.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 2, kind float, dtype float32
d2c/autoencoder/neural_ar_operations.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e68ef3509ca0d2e9 · report fixture: signature t:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
num_samples d2c/autoencoder/lmdb_datasets_modified.py ran MIT (permissive) · 2b4f2e46e841de50 · report fixture: signature dataset:str/0/str, train:bool/0/bool · returned int · level recorded 2026-09-24
reduce_tensor in 32 papers
census: 5 implementations from 6 papers, 3 distinct outputs on one shared input
d2c/autoencoder/utils.py ran MIT (permissive) · be5abd3083ea4db8 · report fixture: signature tensor:Tensor/2/float, world_size:int/0/int · returned Tensor · level recorded 2026-09-24
sample_normal_jit d2c/autoencoder/distributions.py ran MIT (permissive) · 47e78aab5991761b · report fixture: returned tuple · level recorded 2026-09-24
soft_clamp5 in 6 papers d2c/autoencoder/distributions.py ran MIT (permissive) here; the stored copy is pointer only · cd334034d398bfaa · report fixture: returned Tensor · level recorded 2026-09-24
count_parameters_in_M d2c/autoencoder/utils.py unverified MIT (permissive) · 44baea4dbacc4a54 · report
jiamings/d2c_pre_release community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
encoding_steps d2c/diffusion/functions/denoising.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ad14f44fec3d2524 · report fixture: returned list · level recorded 2026-09-22
generalized_steps in 7 papers d2c/diffusion/functions/denoising.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 72677ee06e0271d7 · report fixture: returned tuple · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
compute_alpha in 26 papers repository not located ran · our draft was wrong licence of this copy not recorded · 9215fb189fbfb9f4 · report fixture: signature beta:Tensor/1/float, t:Tensor/1/int · returned Tensor · level recorded 2026-09-22

Tasks

Conditional Image GenerationDenoisingImage GenerationImage ManipulationSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDiffusionPath Length RegularizationR1 RegularizationWeight Demodulation

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