Papers › Consistency Models
Consistency Models
Yang song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever
Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training on these tasks. Consistency models can be trained either by distilling pre-trained diffusion models, or as standalone generative models altogether. Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 for one-step generation. When trained in isolation, consistency models become a new family of generative models that can outperform existing one-step, non-adversarial generative models on standard benchmarks such as CIFAR-10, ImageNet 64x64 and LSUN 256x256.
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 consistency models, 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='consistency models') (how to connect); the free check have('2303.01469') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2303.01469")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2303.01469", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2303.01469")
Code
Syntology 57 code samples: 53 from 7 repositories linked to this paper, 4 identical to code harvested from another paper's repository. Across all 57: 32 ran (of which 5 constructed an object rather than computing a result; 16 with no instrument failure: 5 honoured, 3 violated, 8 with no contract checked; 16 where Syntology's instrument failed) · 25 unverified. Where Syntology's instrument failed: 13 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: 23 samples from 1 repository, 14 ran (4 with no instrument failure; 10 where Syntology's instrument failed); community (archive-listed): 27 samples from 5 repositories, 15 ran (11 with no instrument failure; 4 where Syntology's instrument failed); community: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); 4 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 4 of its repositories that Syntology harvested for other papers:
- cloneofsimo/consistency_models, community (archive-listed): harvested for another paper, listed under the repository
- locuslab/ect, community (archive-listed): harvested for another paper, listed under the repository
- sreerajr000/consistency-models, community (archive-listed): harvested for another paper, listed under the repository
- Mosasaur5526/BCM-iCT-torch, community (archive-listed): harvested for 2 other papers, listed under the repository
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. 6 of the 32 samples that ran have no recorded date.
15 repositories listed; official and paper-mentioned ones first.
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
57 samples harvested: 32 ran (of which 5 constructed an object rather than computing a result; 16 with no instrument failure: 5 honoured, 3 violated, 8 with no contract checked; 16 where Syntology's instrument failed) · 25 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.
Licence: 18 of the 57 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 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 7 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. 4 samples are 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.
8ab9a97df8161f31 · report
fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned ndarray · level recorded, date not recorded census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 cm/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only ·
cfd76fd0d89574a4 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded 53e1de4e44809249 · report
fixture: signature target_ema_mode:str/0/str, start_ema:float/0/float, scale_mode:str/0/str, start_scales:int/0/int, end_scales:int/0/int, total_steps:int/0/int, distill_steps_per_iter:int/0/int · returned function · level recorded 2026-09-25 census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 cm/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only ·
cd33283d615fb3d7 · report
fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded e41367ad14ff58fd · report
fixture: signature named_model_params:list/1/tuple · returned list · level recorded 2026-09-24 b50e02eda098b1ea · report
fixture: signature weight_schedule:str/0/str, snrs:Tensor/1/float, sigma_data:Tensor/1/float · returned Tensor · level recorded 2026-09-25 e20dd5102da3b050 · report
fixture: signature param_groups_and_shapes:list/1/tuple · returned list · level recorded 2026-09-24 bcd8b4acab199405 · report
fixture: signature format:str/0/str, ev_dir:str/0/str, log_suffix:str/0/str · returned HumanOutputFormat · level recorded 2026-09-24 e515a67f7f32e76d · report
fixture: signature comm:MockComm/0/?, local_name2valcount:dict/0/? · returned dict · level recorded 2026-09-26 census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32 cm/losses.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only ·
cf2798b666b231ca · report
fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22 76313eaf1a6e8f2a · report
fixture: signature filename:str/0/str · returned int · level recorded, date not recorded 53d5be4fdbcfac23 · report
fixture: signature pil_image:Image/0/?, image_size:int/0/int, min_crop_frac:float/0/float, max_crop_frac:float/0/float · returned ndarray · level recorded 2026-09-26 64fff1e30802b815 · report
fixture: signature param_group:list/1/tuple, master_param:Tensor/1/float · returned tuple · level recorded 2026-09-24 129b804760b3115f · report
fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-22 35ea054532112e53 · report
7d8e408ce7ec5b07 · report
df72d0c85cc7f5ed · report
84423ecf52775c17 · report
00611e9feba0f93d · report
0c6607473a4c4c55 · report
94e00298a14204fd · report
fixture: returned ConsistencyTrainingOutput · level recorded 2026-09-22 cabb00ce8f3d2b4d · report
fixture: signature num_timesteps:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22 05d51d2b4ba36937 · report
fixture: signature model:callable/0/?, x:Tensor/2/float, sigma:Tensor/1/float, sigma_data:float/0/float, sigma_min:float/0/float, kwargs:dict/0/? · returned Tensor · level recorded 2026-09-22 161fe8043e5391b7 · report
fixture: signature sigma:Tensor/1/float, sigma_data:float/0/float, sigma_min:float/0/float · returned Tensor · level recorded 2026-09-22 97baf73b6f52c910 · report
fixture: signature x:Tensor/2/float, other:Tensor/4/float · returned Tensor · level recorded 2026-09-22 db077dcd1ca85df7 · report
fixture: signature sigma:Tensor/1/float, sigma_data:float/0/float, sigma_min:float/0/float · returned Tensor · level recorded 2026-09-22 c5b94fcc2e72016d · report
0eb7ad1d36660f2e · report
9c21b1af91813988 · report
0438be8b93e89bbb · report
0503d7a3c565cab0 · report
fixture: returned TCDScheduler · level recorded 2026-09-22 1b27854844aa3c28 · report
fixture: returned TCDSchedulerOutput · level recorded 2026-09-22 f1e3f7493aad4745 · report
fixture: signature num_diffusion_timesteps:int/0/int, max_beta:float/0/float, alpha_transform_type:str/0/str · returned Tensor · level recorded 2026-09-22 64b2196de5dcf1e5 · report
fixture: signature betas:Tensor/1/float · returned Tensor · level recorded 2026-09-22 705aea0955c9050d · report
fixture: signature a:ArrayImpl/2/float, b:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22 05252c6abda35d7f · report
f9e4398d47ea4296 · report
fixture: returned QKVAttentionLegacy · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket unet/student_unet.py ran MIT (permissive) ·
8aa58874f24b2a76 · report
fixture: signature x:Tensor/4/float, emb:Tensor/2/float · returned Tensor · level recorded 2026-09-24 census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket unet/student_unet.py ran · our draft was wrong MIT (permissive) ·
703cead614cf486e · report
fixture: signature channels:int/0/int · returned GroupNorm · level recorded 2026-09-22 962837b1727d71b7 · report
2e8d0cb0b59bdbd1 · report
9ce7073af820d275 · report
d94e99bfc711955c · report
fixture: returned PCMFMDeterministicSchedulerOutput · level recorded 2026-09-22 6d1af0f005c519b3 · report
9b13a9bca59f4324 · report
841087e80145f348 · report
4 samples are 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.
a05b1d0cf3f508b4 · report
fixture: signature cls:callable/0/?, name:NoneType/0/? · returned type · level recorded, date not recorded 473066ddf62a075a · report
fixture: signature cls:callable/0/?, name:NoneType/0/? · returned type · level recorded, date not recorded 5d181060fa21e0cc · report
fixture: signature current_training_step:int/0/int, total_training_steps:int/0/int, initial_timesteps:int/0/int, final_timesteps:int/0/int · returned int · level recorded 2026-09-22 a58facb8fe71823a · 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. 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. 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". 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. 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.
6 assemblies on this paper: 5 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).
generated Assembly for consistency models (graph method: consistency models), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 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)
- consistency_model_editing_step entry · level 3 · ran; the contract check could not run ·
732d418a8fe3609415c9d36a828df2df49a64df4740208b078aa16a8dedab1f6
5 sibling assemblies for consistency 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 consistency models (graph method: consistency models). 8 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 5 siblings
- ConsistencyTraining entry · level 0 · unverified ·
c5b94fcc2e72016d - ConsistencyTrainingOutput helper · level 1 · ran ·
94e00298a14204fd - karras_schedule scheduler · level 1 · ran · honoured contract ·
cabb00ce8f3d2b4d - model_forward_wrapper helper · level 1 · ran; the contract check could not run (RAISES) ·
05d51d2b4ba36937 - pad_dims_like helper · level 1 · ran; the contract check could not run (RAISES) ·
97baf73b6f52c910 - timesteps_schedule scheduler · level 1 · ran · honoured contract ·
5d181060fa21e0cc - output_scaling helper · level 1 · ran · violated contract ·
161fe8043e5391b7 - skip_scaling helper · level 1 · ran · violated contract ·
db077dcd1ca85df7
harvested Assembly for consistency models (graph method: consistency models). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 5 siblings
- TCDScheduler entry · level 1 · ran ·
0503d7a3c565cab0 - TCDSchedulerOutput helper · level 1 · ran ·
1b27854844aa3c28 - betas_for_alpha_bar helper · level 1 · ran · honoured contract ·
f1e3f7493aad4745 - rescale_zero_terminal_snr helper · level 1 · ran · our draft was wrong ·
64b2196de5dcf1e5
harvested Assembly for consistency models (graph method: consistency models). 2 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 5 siblings
- PCMFMDeterministicScheduler entry · level 0 · unverified ·
6d1af0f005c519b3 - PCMFMDeterministicSchedulerOutput helper · level 1 · ran ·
d94e99bfc711955c
harvested Assembly for consistency models (graph method: consistency models). 17 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.
one of 5 siblings
- ShiftUNet entry · level 0 · unverified ·
b9b7422c33b745d9 - AttentionBlock model · level 0 · unverified ·
962837b1727d71b7 - ResBlock model · level 1 · ran ·
8aa58874f24b2a76 - ResBlockShift model · level 0 · unverified ·
b56ce6f9b307e9e5 - TimestepEmbedSequential helper · level 0 · unverified ·
9ce7073af820d275 - conv_nd helper · level 0 · unverified ·
fe4eb545bbb728e0 - linear helper · level 1 · ran · our draft was wrong ·
0e30585f04efffbe - normalization helper · level 1 · ran · our draft was wrong ·
703cead614cf486e - timestep_embedding helper · level 1 · ran · our draft was wrong ·
270cd726f1952c2a - zero_module helper · level 1 · ran · our draft was wrong ·
129b804760b3115f - QKVAttention model · level 1 · ran ·
afd1425583888760 - QKVAttentionLegacy model · level 1 · ran ·
f9e4398d47ea4296 - Downsample helper · level 1 · ran ·
8c5676227adb2492 - TimestepBlock helper · level 0 · unverified ·
2e8d0cb0b59bdbd1 - Upsample helper · level 1 · ran ·
6998a3677700ee6c - TimestepZBlock helper · level 0 · unverified ·
787099a78454d6ac - avg_pool_nd helper · level 0 · unverified ·
ecd0fc28815b65ae
harvested Assembly for consistency models (graph method: consistency models). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 5 siblings
- get_consistency_loss_fn entry · level 0 · unverified ·
05252c6abda35d7f - batch_mul helper · level 1 · ran · violated contract ·
705aea0955c9050d
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="2303.01469") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | CIFAR-10 | CT (Direct Generation, NFE=2) | FID | 5.83 | #35 of 78 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CD (Diffusion + Distillation, NFE=2) | FID | 4.70 | #24 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CD (Diffusion + Distillation, NFE=2) | NFE | 2 | #24 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CD (Diffusion + Distillation, NFE=1) | FID | 6.20 | #25 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CD (Diffusion + Distillation, NFE=1) | NFE | 1 | #25 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CT (Direct Generation, NFE=2) | FID | 11.1 | #26 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CT (Direct Generation, NFE=2) | NFE | 2 | #26 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CT (Direct Generation, NFE=1) | FID | 13.0 | #27 of 65 | Archive leaderboard | report |
| Image Generation | ImageNet 64x64 | CT (Direct Generation, NFE=1) | NFE | 1 | #27 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
Introduced by this paper: Consistency Models
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