Papers › Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion...

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation

5 Apr 2024arXiv:2404.04057archive 2025-07-28

Mingyuan Zhou, Huangjie Zheng, Zhendong Wang, Mingzhang Yin, Hai Huang

We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator. SiD not only facilitates an exponentially fast reduction in Fréchet inception distance (FID) during distillation but also approaches or even exceeds the FID performance of the original teacher diffusion models. By reformulating forward diffusion processes as semi-implicit distributions, we leverage three score-related identities to create an innovative loss mechanism. This mechanism achieves rapid FID reduction by training the generator using its own synthesized images, eliminating the need for real data or reverse-diffusion-based generation, all accomplished within significantly shortened generation time. Upon evaluation across four benchmark datasets, the SiD algorithm demonstrates high iteration efficiency during distillation and surpasses competing distillation approaches, whether they are one-step or few-step, data-free, or dependent on training data, in terms of generation quality. This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation. The PyTorch implementation is available at https://github.com/mingyuanzhou/SiD

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.

Syntology holds a reference implementation of Score identity Distillation (SiD), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Score identity Distillation (SiD)') (how to connect); the free check have('2404.04057') needs no token.

For agents, on Syntology's MCP service (how to connect):

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; 7 with no instrument failure: 4 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 10 ran (7 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.

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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 10 samples that ran have no recorded date.

mingyuanzhou/sid officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 10 ran (3 instrument-failed) · 5 unverified report
mingyuanzhou/sid-lsg mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation (arXiv:2406.01561; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 5 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

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 1 violated, 2 with no contract checked; 3 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.

4ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
2ran
5unverified

Licence: 4 of the 15 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 mingyuanzhou/sid. “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.

mingyuanzhou/sid official repository 15 samples, 10 ran (3 instrument-failed) · 5 unverified
calculate_fid_from_inception_stats in 26 papers sid_generate.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 68b5e143931956cf · report fixture: signature mu:ndarray/1/float, sigma:ndarray/2/float, mu_ref:ndarray/1/float, sigma_ref:ndarray/2/float · returned float · level recorded 2026-09-22
compute_distances in 10 papers metrics/sid_precision_recall.py ran Apache-2.0 (permissive) · 790b320b90341326 · report fixture: signature row_features:Tensor/2/float, col_features:Tensor/2/float, num_gpus:int/0/int, rank:int/0/int, col_batch_size:int/0/int · returned Tensor · level recorded 2026-09-24
file_ext in 37 papers dataset_tool.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
get_feature_detector_name metrics/sid_metric_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c127dc46d6966547 · report fixture: signature url:str/0/str · returned str · level recorded 2026-09-25
is_valid_metric metrics/sid_metric_main.py ran · violated contract Apache-2.0 (permissive) · 147acc22e758c8e5 · report fixture: signature metric:str/0/str · returned bool · level recorded 2026-09-24
maybe_min in 36 papers dataset_tool.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
parse_int_list in 59 papers sid_metrics.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
parse_tuple in 34 papers dataset_tool.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 07b21b35ecb4815c · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-24
register_metric metrics/sid_metric_main.py ran · our draft was wrong Apache-2.0 (permissive) · e574c21e7f007b61 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
setup_snapshot_image_grid in 5 papers training/sid_training_loop.py ran Apache-2.0 (permissive) · 41d0a46d745163d4 · report fixture: signature training_set:MockTrainingSet/0/?, random_seed:int/0/int · returned tuple · level recorded 2026-09-24
compute_fid in 5 papers metrics/sid_frechet_inception_distance.py unverified Apache-2.0 (permissive) · a7058b1ccaa13516 · report
compute_is in 10 papers metrics/sid_inception_score.py unverified Apache-2.0 (permissive) · 47c7a1249e324f74 · report
compute_kid metrics/sid_kernel_inception_distance.py unverified Apache-2.0 (permissive) · 5dd3f075a53b2c58 · report
compute_pr metrics/sid_precision_recall.py unverified Apache-2.0 (permissive) · b657531c701b1786 · report
sid_sampler sid_generate.py unverified Apache-2.0 (permissive) · 4c9c2d2ca6c238d8 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

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

generated Assembly for Score identity Distillation (SiD) (graph method: Score identity Distillation (SiD)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. sid_generator_loss entry · level 3 · ran · honoured contract · b4622955b6faba67e342de8a94df720e123b224af3c6b0fbae58c622658d968a

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="2404.04057") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation AFHQ-v2 64x64 SiD FID 1.711 #2 of 2 Archive leaderboard report
Image Generation AFHQ-v2 64x64 SiD NFE 1 #2 of 2 Archive leaderboard report
Image Generation CIFAR-10 SiD FID 1.71 #8 of 78 Archive leaderboard report
Image Generation CIFAR-10 SiD NFE 1 #8 of 78 Archive leaderboard report
Image Generation FFHQ 64x64 SiD FID 1.55 #2 of 2 Archive leaderboard report
Image Generation FFHQ 64x64 SiD NFE 1 #2 of 2 Archive leaderboard report
Image Generation ImageNet 64x64 SiD FID 1.524 #13 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 SiD NFE 1 #13 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

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