Papers › Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

1 Oct 2023arXiv:2310.02279archive 2025-07-28

Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon

Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion process. CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance and achieves new state-of-the-art FIDs for single-step diffusion model sampling on CIFAR-10 (FID 1.73) and ImageNet at 64x64 resolution (FID 1.92). CTM also enables a new family of sampling schemes, both deterministic and stochastic, involving long jumps along the ODE solution trajectories. It consistently improves sample quality as computational budgets increase, avoiding the degradation seen in CM. Furthermore, unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods from the diffusion community. This access also enables the computation of likelihood. The code is available at https://github.com/sony/ctm.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.02279")

Code

Syntology Ran 14 of 18 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 6 ran · our draft was wrong; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 18 samples from 2 repositories, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sony/ctm officialmentioned in papermentioned on GitHubpytorchMIT report
Kim-Dongjun/ctm-cifar10 officialpytorchMIT 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

18 samples harvested; 14 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
6ran · our draft was wrong
1ran · fixture could not drive it
6ran
4unverified

Licence: 0 of the 18 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

NormLayer Kim-Dongjun/ctm-cifar10/pg_modules/blocks.py official repository ran · our draft was wrong MIT (permissive) · ef1e7dffb5d433d4 · report
UpBlockBig Kim-Dongjun/ctm-cifar10/pg_modules/blocks.py official repository ran MIT (permissive) · f87cd99314206f72 · report
UpBlockSmall Kim-Dongjun/ctm-cifar10/pg_modules/blocks.py official repository ran MIT (permissive) · 0186912dcb8b92b9 · report
approx_standard_normal_cdf Kim-Dongjun/ctm-cifar10/cm/losses.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · cfd76fd0d89574a4 · report
calculate_fid_from_inception_stats Kim-Dongjun/ctm-cifar10/fid_npzs.py official repository ran MIT (permissive) · e503281a27d647f2 · report
discretized_gaussian_log_likelihood Kim-Dongjun/ctm-cifar10/cm/losses.py official repository ran · our draft was wrong MIT (permissive) · cd33283d615fb3d7 · report
format_time Kim-Dongjun/ctm-cifar10/dnnlib/util.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 674eca7b9e1b6439 · report
format_time_brief Kim-Dongjun/ctm-cifar10/dnnlib/util.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 32af001972a0699f · report
forward_flex Kim-Dongjun/ctm-cifar10/feature_networks/vit.py official repository ran MIT (permissive) · 562cccfa5027f008 · report
get_activation Kim-Dongjun/ctm-cifar10/feature_networks/vit.py official repository ran · our draft was wrong MIT (permissive) · 1c094193a4506a40 · report
get_importance_time Kim-Dongjun/ctm-cifar10/eval_bpd.py official repository ran MIT (permissive) · a9714b52e1f9cae4 · report
normal_kl Kim-Dongjun/ctm-cifar10/cm/losses.py official repository ran · honoured contract fingerprinted MIT (permissive) · cf2798b666b231ca · report
normalizing_Z Kim-Dongjun/ctm-cifar10/eval_bpd.py official repository ran MIT (permissive) · 184f71c18a7adc90 · report
weight_init Kim-Dongjun/ctm-cifar10/cm/networks.py official repository ran · fixture could not drive it MIT (permissive) · d41a4250066bce93 · report
ask_yes_no Kim-Dongjun/ctm-cifar10/dnnlib/util.py official repository unverified MIT (permissive) · 9d31d2c4cd16bb2d · report
forward_vit Kim-Dongjun/ctm-cifar10/feature_networks/vit.py official repository unverified MIT (permissive) · 4c52162336ee4320 · report
gen_get_importance_time Kim-Dongjun/ctm-cifar10/eval_bpd.py official repository unverified MIT (permissive) · f1094afb0c4007e4 · report
get_classifier_guidance sony/ctm/code/classifier_rejection.py official repository unverified MIT (permissive) · f791227ca49fdf0b · report

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 64x64 CTM FID 1.73 #17 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 CTM Inception Score 64.29 #17 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 CTM NFE 2 #17 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 CTM (NFE 1) Inception Score 70.38 #64 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 CTM (NFE 1) NFE 1 #64 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

Denoising Score MatchingDiffusion

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