SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.02398 · 2024

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.02398.json · badge: /api/ran/2407.02398.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yangling0818/consistency_flow_matching canonical (classifier label)
classifier basis: plan_row
11 ran · 2 no recorded run
FunctionStatusWhere it lives
crop_resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yangling0818/consistency_flow_matching/datasets.py
pointer only (licence: MIT); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("fd14d238ccd5f679")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rarazafin/score_diffusion_ensemble, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_act Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/models/layers.py
code served (permissive licence) · get_code("db5f935a1d6b4c2c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ReLU. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class Config:
    def __init__(self, nonlinearity):
        self.model = self
        self.nonlinearity = nonlinearity

# Test with 'relu' as the nonlinearity
config = Config('relu')

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_data_inverse_scaler Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/datasets.py
code served (permissive licence) · get_code("6c419026e778dee2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from types import SimpleNamespace

torch.manual_seed(0)

# Build a minimal config object with a data attribute that has a 'centered' field
config = SimpleNamespace()
config.data = SimpleNamespace()
config.data.centered = True

ARGS = {
    "config": config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_data_scaler Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/datasets.py
code served (permissive licence) · get_code("346d2e6cc8b48a5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from types import SimpleNamespace

torch.manual_seed(0)

# Create a minimal config object with the data.centered attribute
config = SimpleNamespace(
    data=SimpleNamespace(
        centered=True
    )
)

ARGS = {
    "config": config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_div_fn Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/likelihood.py
pointer only (licence: MIT); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("0bfcb6b2d940e393")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rarazafin/score_diffusion_ensemble, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_normalization Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/models/normalization.py
code served (permissive licence) · get_code("1b8adb3294e53c6d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned type. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal config class with the required attributes
class Config:
    def __init__(self):
        self.model = ModelConfig()

class ModelConfig:
    def __init__(self):
        self.normalization = 'InstanceNorm++'
        self.num_classes = 5

# Create config instances for different test cases
config_conditional = Config()
config_conditional.model.normalization = 'InstanceNorm++'
config_conditional.model.num_classes = 5

config_non_conditional_instance = Config()
config_non_conditional_instance.model.normalization = 'InstanceNorm++'

config_non_conditional_variance = Config()
config_non_conditional_variance.model.normalization = 'VarianceNorm'

config_non_conditional_instance_norm = Config()
config_non_conditional_instance_norm.model.normalization = 'InstanceNorm'

config_non_conditional_groupnorm = Config()
config_non_conditional_groupnorm.model.normalization = 'GroupNorm'

ARGS = {
    'config': config_non_conditional_instance,
    'conditional': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_optimizer Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("8ff7c24dade9904c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hfmei/idc, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ncsn_conv1x1 Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/models/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from SusanneSchaub/TPDM_Implant_Inpainting, is pointer only (licence: NONE) · get_code("85b2235eb7afaa4f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from SusanneSchaub/TPDM_Implant_Inpainting, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

optimization_manager Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("366bb8c7035a2fc8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hfmei/idc, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_t_like_x Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/consistencyfm/torchcfm/conditional_flow_matching.py
code served (permissive licence) · get_code("9e320fdaa5a3063f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 1, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a batch of 2 samples with 3 channels, width 4, height 5
x = torch.randn(2, 3, 4, 5)

# Create a time vector with batch size 2
t = torch.randn(2)

ARGS = {
    't': t,
    'x': x
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 1, 1) — shape (2, 1, 1, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
variance_scaling Ran
ran; our contract draft was wrong, not the code
yangling0818/consistency_flow_matching/models/layers.py
code served (permissive licence) · get_code("3ac11bfe0ae80195")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'scale': 2.0,
    'mode': 'fan_in',
    'distribution': 'normal',
    'in_axis': 1,
    'out_axis': 0,
    'dtype': torch.float32,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
classifier_fn_from_tfhub Not yet run
unverified (harvested, no recorded run)
yangling0818/consistency_flow_matching/evaluation.py
pointer only (licence: MIT); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("54a00db9aadf092f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rarazafin/score_diffusion_ensemble, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_dataset_stats Not yet run
unverified (harvested, no recorded run)
yangling0818/consistency_flow_matching/evaluation.py
pointer only (licence: MIT); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("b45ab263f8440954")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rarazafin/score_diffusion_ensemble, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 7 the same month, 13 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
variance_scaling 28 other papers
19 dated earlier, 2 the same month, 7 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 25 more not named here
ncsn_conv1x1 19 other papers
12 dated earlier, 2 the same month, 5 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 16 more not named here
get_data_inverse_scaler 17 other papers
14 dated earlier, 1 the same month, 2 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
get_data_scaler 17 other papers
14 dated earlier, 1 the same month, 2 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
get_act 16 other papers
11 dated earlier, 2 the same month, 3 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
optimization_manager 16 other papers
15 dated earlier, 1 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
get_optimizer 15 other papers
14 dated earlier, 1 later
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
and 12 more not named here
crop_resize 13 other papers
11 dated earlier, 1 the same month, 1 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 10 more not named here
get_div_fn 11 other papers
10 dated earlier, 1 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2205.13699 (2022-05)
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
and 8 more not named here
classifier_fn_from_tfhub 9 other papers
8 dated earlier, 1 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2205.13699 (2022-05)
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
2206.05564 (2022-06)
gDDIM: Generalized denoising diffusion implicit models
and 6 more not named here
get_normalization 7 other papers
2 dated earlier, 2 the same month, 3 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2405.18816 (2024-05)
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
2407.10641 (2024-07)
Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems
and 4 more not named here
pad_t_like_x 6 other papers
3 dated earlier, 3 later · 2 only as an assembly brick
2302.00482 (2023-02)
Improving and generalizing flow-based generative models with minibatch optimal transport
2307.03672 (2023-07)
Simulation-free Schrödinger bridges via score and flow matching
2405.15252 (2024-05)
Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport
and 3 more not named here
load_dataset_stats 5 other papers
4 dated earlier, 1 later
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2210.04296 (2022-10)
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation
and 2 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate high-quality samples with fewer function evaluations, typically through iterative rectification methods or optimal transport solutions. In this paper, we introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Consistency-FM directly defines straight flows starting from different times to the same endpoint, imposing constraints on their velocity values. Additionally, we propose a multi-segment training approach for Consistency-FM to enhance expressiveness, achieving a better trade-off between sampling quality and speed. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models and 1.7x faster than rectified flow models while achieving better generation quality. Our code is available at: https://github.com/YangLing0818/consistency_flow_matching

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.02398")
get_code_for_paper("2407.02398")
have("2407.02398")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.02398.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.02398.svg)](https://syntology.ai/paper/2407.02398)

Connect an agent — have() is free.