SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01469 · ICML · 2023

Consistency Models

Yang Song, Mark Chen, Prafulla Dhariwal, Ilya Sutskever

arXiv · PDF · Open in the Atlas

Code that ran

32 of 57 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 3 violated it and 7 have no contract verdict; 17 failures of our instrument; 25 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2303.01469.json · badge: /api/ran/2303.01469.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
openai/consistency_models canonical (classifier label)
classifier basis not recorded on the link
14 ran · 9 no recorded run
openai/consistency_models_cifar10 canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
Kinyugo/consistency_models reimplementation (classifier label)
classifier basis: classifier_2025
6 ran · 4 no recorded run
jabir-zheng/TCD community
Papers with Code archive
4 ran · 0 no recorded run
sainzerjj/sferd community
Papers with Code archive
3 ran · 6 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 1 no recorded run
G-U-N/Phased-Consistency-Model community
Papers with Code archive
1 ran · 1 no recorded run
crowsonkb/consistency-models reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
center_crop_arr Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/image_datasets.py
code served (permissive licence) · get_code("8ab9a97df8161f31")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ndarray, ndim 3, dtype family int, shape (64, 64, 3) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:51:18Z). 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.

from PIL import Image
import numpy as np

# Create a small PIL Image for testing
# Make it larger than 2 * image_size so we can test the resizing logic
pil_image = Image.new('RGB', (256, 256), color='red')

# Define image_size parameter
image_size = 64

# Construct ARGS dictionary
ARGS = {
    'pil_image': pil_image,
    'image_size': image_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (64, 64, 3) — shape (64, 64, 3) 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
ConsistencyTrainingOutput Ran
ran on a synthesized input · constructed an object; no result was computed
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("94e00298a14204fd")
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 an instance of its own class, ConsistencyTrainingOutput: the run constructed the object and did not call it, so no result was computed. 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
from dataclasses import dataclass
from typing import Optional
from torch import Tensor

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# batch_size=2, feature_dim=4
predicted = torch.randn(2, 4)
target = torch.randn(2, 4)
num_timesteps = 10
sigmas = torch.randn(2)
loss_weights = torch.randn(2)

ARGS = {
    "predicted": predicted,
    "target": target,
    "num_timesteps": num_timesteps,
    "sigmas": sigmas,
    "loss_weights": loss_weights,
}
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 ConsistencyTrainingOutput — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConsistencyTrainingOutput 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
PCMFMDeterministicSchedulerOutput Ran
ran on a synthesized input · constructed an object; no result was computed
G-U-N/Phased-Consistency-Model/code/text_to_image_sd3/pcm_fm_deterministic_scheduler.py
code served (permissive licence) · get_code("d94e99bfc711955c")
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 an instance of its own class, PCMFMDeterministicSchedulerOutput: the run constructed the object and did not call it, so no result was computed. 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 dataclasses import dataclass
from diffusers.utils import BaseOutput

torch.manual_seed(0)

@dataclass
class PCMFMDeterministicSchedulerOutput(BaseOutput):
    prev_sample: torch.FloatTensor

# Create a small tensor with shape (2, 4) for prev_sample
prev_sample = torch.randn(2, 4)

ARGS = {
    "prev_sample": prev_sample,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
diffusers, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PCMFMDeterministicSchedulerOutput — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PCMFMDeterministicSchedulerOutput 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
QKVAttentionLegacy Ran
ran on a synthesized input · constructed an object; no result was computed
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("f9e4398d47ea4296")
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 an instance of its own class, QKVAttentionLegacy: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

# The QKVAttentionLegacy class expects:
# - n_heads: int, number of attention heads
# - forward input qkv: tensor of shape [N x (H * 3 * C) x T]
#   where N is batch size, H is n_heads, C is channel dim per head, T is sequence length

# Let's construct valid inputs:
# batch size N = 2
# n_heads H = 4
# channel per head C = 3
# sequence length T = 5

n_heads = 4
ch = 3  # channels per head
batch_size = 2
seq_length = 5

# width = H * 3 * C (concatenated Q, K, V)
width = n_heads * 3 * ch  # = 4 * 3 * 3 = 36

# Create qkv tensor of shape [N x (H * 3 * C) x T]
qkv = torch.randn(batch_size, width, seq_length)

ARGS = {
    "n_heads": n_heads,
}
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 QKVAttentionLegacy — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a QKVAttentionLegacy 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
ResBlock Ran
ran on a synthesized input
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("8aa58874f24b2a76")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import torch.nn.functional as F

def avg_pool_nd(dims, *args, **kwargs):
    if dims == 1:
        return nn.AvgPool1d(*args, **kwargs)
    elif dims == 2:
        return nn.AvgPool2d(*args, **kwargs)
    elif dims == 3:
        return nn.AvgPool3d(*args, **kwargs)
    raise ValueError(f'unsupported dimensions: {dims}')

def conv_nd(dims, *args, **kwargs):
    if dims == 1:
        return nn.Conv1d(*args, **kwargs)
    elif dims == 2:
        return nn.Conv2d(*args, **kwargs)
    elif dims == 3:
        return nn.Conv3d(*args, **kwargs)
    raise ValueError(f'unsupported dimensions: {dims}')

def linear(*args, **kwargs):
    return nn.Linear(*args, **kwargs)

def normalization(channels):
    return nn.GroupNorm(32, channels)

def zero_module(module):
    for p in module.parameters():
        p.detach().zero_()
    return module

class TimestepBlock(nn.Module):
    def forward(self, x, emb):
        pass

class Upsample(nn.Module):
    def __init__(self, channels, use_conv, dims=2, out_channels=None):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        if use_conv:
            self.conv = conv_nd(dims, self.channels, self.out_channels, 3, padding=1)

    def forward(self, x):
        assert x.shape[1] == self.channels
        if self.dims == 3:
            x = F.interpolate(x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode='nearest')
        else:
            x = F.interpolate(x, scale_factor=2, mode='nearest')
        if self.use_conv:
            x = self.conv(x)
        return x

class Downsample(nn.Module):
    def __init__(self, channels, use_conv, dims=2, out_channels=None):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        stride = 2 if dims != 3 else (1, 2, 2)
        if use_conv:
            self.op = conv_nd(dims, self.channels, self.out_channels, 3, stride=stride, padding=1)
        else:
            assert self.channels == self.out_channels
            self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)

    def forward(self, x):
        assert x.shape[1] == self.channels
        return self.op(x)

class ResBlock(TimestepBlock):
    def __init__(self, channels, emb_channels, dropout, out_channels=None, use_conv=False, dims=2, up=False, down=False):
        super().__init__()
        self.channels = channels
        self.emb_channels = emb_channels
        self.dropout = dropout
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.in_layers = nn.Sequential(normalization(channels), nn.SiLU(), conv_nd(dims, channels, self.out_channels, 3, padding=1))
        self.updown = up or down
        if up:
            self.h_upd = Upsample(channels, False, dims)
            self.x_upd = Upsample(channels, False, dims)
        elif down:
            self.h_upd = Downsample(channels, False, dims)
            self.x_upd = Downsample(channels, False, dims)
        else:
            self.h_upd = self.x_upd = nn.Identity()
        
        self.emb_layers = nn.Sequential(nn.SiLU(), linear(emb_channels, self.out_channels))
        self.out_layers = nn.Sequential(
            normalization(self.out_channels),
            nn.SiLU(),
            nn.Dropout(p=dropout),
            zero_module(conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1))
        )
        
        if self.out_channels == channels:
            self.skip_connection = nn.Identity()
        elif use_conv:
            self.skip_connection = conv_nd(dims, channels, self.out_channels, 3, padding=1)
        else:
            self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)

    def forward(self, x, emb):
        if self.updown:
            in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1]
            h = in_rest(x)
            h = self.h_upd(h)
            x = self.x_upd(x)
            h = in_conv(h)
        else:
            h = self.in_layers(x)
        
        emb_out = self.emb_layers(emb)
        while len(emb_out.shape) < len(h.shape):
            emb_out = emb_out[..., None]
        h = h + emb_out
        h = self.out_layers(h)
        return self.skip_connection(x) + h

INIT_ARGS = {
    'channels': 64,
    'emb_channels': 128,
    'dropout': 0.1,
    'out_channels': 96,
    'use_conv': True,
    'dims': 2,
    'up': True,
    'down': False
}

ARGS = {
    'x': torch.randn(2, 64, 8, 12),
    'emb': torch.randn(2, 128)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
TCDScheduler Ran
ran on a synthesized input · constructed an object; no result was computed
jabir-zheng/TCD/scheduling_tcd.py
pointer only (licence: NONE) · get_code("0503d7a3c565cab0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jabir-zheng/TCD 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.

TCDSchedulerOutput Ran
ran on a synthesized input · constructed an object; no result was computed
jabir-zheng/TCD/scheduling_tcd.py
pointer only (licence: NONE) · get_code("1b27854844aa3c28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jabir-zheng/TCD 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.

approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
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 quandao10/slct, 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.

batch_mul Ran
ran, violated the contract we drafted
openai/consistency_models_cifar10/jcm/losses.py
code served (permissive licence) · get_code("705aea0955c9050d")
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 ArrayImpl, ndim 2, dtype family float, shape (2, 4) 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 jax
import jax.numpy as jnp

def batch_mul(a, b):
    return jax.vmap(lambda a, b: a * b)(a, b)

# Create small JAX arrays with batch dimension
# batch_mul uses vmap to apply element-wise multiplication across batches
# a and b should be arrays where the first dimension is the batch dimension

a = jnp.ones((2, 4))  # batch size 2, inner dimension 4
b = jnp.ones((2, 4))  # batch size 2, inner dimension 4

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
jabir-zheng/TCD/scheduling_tcd.py
pointer only (licence: NONE) · get_code("f1e3f7493aad4745")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jabir-zheng/TCD 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.

create_ema_and_scales_fn Ran
ran on a synthesized input
openai/consistency_models/cm/script_util.py
code served (permissive licence) · get_code("53e1de4e44809249")
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 numpy as np

ARGS = {
    'target_ema_mode': 'fixed',
    'start_ema': 0.99,
    'scale_mode': 'fixed',
    'start_scales': 4,
    'end_scales': 8,
    'total_steps': 1000,
    'distill_steps_per_iter': 100,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
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 quandao10/slct, 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_param_groups_and_shapes Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/fp16_util.py
pointer only (licence: MIT); the stored copy get_code serves, from ZhendongWang6/DIRE, is pointer only (licence: NONE) · get_code("e41367ad14ff58fd")
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 ZhendongWang6/DIRE, 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_weightings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
openai/consistency_models/cm/karras_diffusion.py
code served (permissive licence) · get_code("b50e02eda098b1ea")
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 Tensor, ndim 1, dtype family float, shape (4,) 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 as th

th.manual_seed(0)

# Create small tensors for snrs and sigma_data
# snrs: signal-to-noise ratios tensor
snrs = th.tensor([1.0, 2.0, 3.0, 4.0])

# sigma_data: noise level parameter
sigma_data = th.tensor([0.5, 0.6, 0.7, 0.8])

# weight_schedule: string parameter that determines which weighting scheme to use
weight_schedule = 'snr'

ARGS = {
    'weight_schedule': weight_schedule,
    'snrs': snrs,
    'sigma_data': sigma_data,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
karras_schedule Ran
ran, honoured the contract we drafted
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("cabb00ce8f3d2b4d")
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 Tensor, ndim 1, dtype family float, shape (10,) 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)

ARGS = {
    "num_timesteps": 10,
    "sigma_min": 0.002,
    "sigma_max": 80.0,
    "rho": 7.0,
    "device": torch.device("cpu"),
}
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 Tensor, ndim 1, dtype family float, shape (10,) — shape (10,) 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
make_master_params Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/fp16_util.py
pointer only (licence: MIT); the stored copy get_code serves, from ZhendongWang6/DIRE, is pointer only (licence: NONE) · get_code("e20dd5102da3b050")
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 ZhendongWang6/DIRE, 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.

make_output_format Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/logger.py
code served (permissive licence) · get_code("bcd8b4acab199405")
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 HumanOutputFormat. 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 os
import sys
import tempfile

# Create a temporary directory for output
temp_dir = tempfile.mkdtemp()

ARGS = {
    'format': 'log',
    'ev_dir': temp_dir,
    'log_suffix': '_test'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type HumanOutputFormat — a HumanOutputFormat output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a HumanOutputFormat 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
model_forward_wrapper Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("05d51d2b4ba36937")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model that takes x and sigma as inputs
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=4):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x, sigma, **kwargs):
        # The model receives x and sigma, processes x
        return self.linear(x)

# Create model instance
model = SimpleModel(input_dim=4, output_dim=4)

# Create input tensors
# x: noisy samples with shape (batch=2, features=4)
x = torch.randn(2, 4)

# sigma: standard deviation of noise, shape (batch=2,) 
sigma = torch.randn(2)

# Parameters with default values
sigma_data = 0.5
sigma_min = 0.002

# Additional kwargs to pass to model
kwargs = {}

ARGS = {
    "model": model,
    "x": x,
    "sigma": sigma,
    "sigma_data": sigma_data,
    "sigma_min": sigma_min,
    "kwargs": kwargs
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
mpi_weighted_mean Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/logger.py
pointer only (licence: MIT); the stored copy get_code serves, from HeadLiuYun/NeuroDiff, is pointer only (licence: NONE) · get_code("e515a67f7f32e76d")
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 HeadLiuYun/NeuroDiff, 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.

normal_kl Ran
ran, honoured the contract we drafted
openai/consistency_models/cm/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
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 facebookresearch/agrol, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

normalization Ran
ran; our contract draft was wrong, not the code
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("703cead614cf486e")
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 GroupNorm. 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)

# The normalization function takes 'channels' as a parameter
# It returns nn.GroupNorm(32, channels), which expects:
# - num_groups: 32 (fixed)
# - num_channels: the input channels parameter
# 
# We need to provide a valid number of channels.
# GroupNorm requires num_channels to be divisible by num_groups,
# so channels should be divisible by 32.

channels = 64  # divisible by 32, allows valid GroupNorm construction

ARGS = {
    "channels": channels
}
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 GroupNorm — a GroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm 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
output_scaling Ran
ran, violated the contract we drafted
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("161fe8043e5391b7")
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 Tensor, ndim 1, dtype family float, shape (4,) 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)

# sigma is a Tensor that represents noise standard deviation
# It can be a scalar or batched tensor
sigma = torch.tensor([0.1, 0.5, 1.0, 2.0], dtype=torch.float32)

# sigma_data is the standard deviation of the data (float)
sigma_data = 0.5

# sigma_min is the minimum noise standard deviation from the karras schedule (float)
sigma_min = 0.002

ARGS = {
    "sigma": sigma,
    "sigma_data": sigma_data,
    "sigma_min": sigma_min,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
pad_dims_like Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("97baf73b6f52c910")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 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 two tensors with different numbers of dimensions
# x has fewer dimensions than other
x = torch.randn(2, 4)  # 2D tensor with shape (2, 4)
other = torch.randn(2, 4, 3, 5)  # 4D tensor with shape (2, 4, 3, 5)

ARGS = {
    "x": x,
    "other": other,
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 1, 1) — shape (2, 4, 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
parse_resume_step_from_filename Ran
ran, honoured the contract we drafted
openai/consistency_models/cm/train_util.py
pointer only (licence: MIT); the stored copy get_code serves, from zzzhangboya/scoreopt, is pointer only (licence: NONE) · get_code("76313eaf1a6e8f2a")
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 zzzhangboya/scoreopt, 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.

random_crop_arr Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/image_datasets.py
code served (permissive licence) · get_code("53d5be4fdbcfac23")
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 ndarray, ndim 3, dtype family int, shape (64, 64, 3) 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 math
import random
from PIL import Image
import numpy as np

# Create a simple PIL Image for testing
# Make it large enough that cropping operations make sense
width, height = 256, 256
pil_image = Image.new('RGB', (width, height), color='red')

# Fill with some variation so it's not completely uniform
pixels = pil_image.load()
for i in range(width):
    for j in range(height):
        pixels[i, j] = (i % 256, j % 256, (i + j) % 256)

# Define parameters
image_size = 64
min_crop_frac = 0.8
max_crop_frac = 1.0

ARGS = {
    'pil_image': pil_image,
    'image_size': image_size,
    'min_crop_frac': min_crop_frac,
    'max_crop_frac': max_crop_frac,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (64, 64, 3) — shape (64, 64, 3) 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
register_corrector Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from yang-song/score_sde_pytorch
pointer only · get_code("a05b1d0cf3f508b4")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

register_predictor Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from yang-song/score_sde_pytorch
pointer only · get_code("473066ddf62a075a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

rescale_zero_terminal_snr Ran
ran; our contract draft was wrong, not the code
jabir-zheng/TCD/scheduling_tcd.py
pointer only (licence: NONE) · get_code("64b2196de5dcf1e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jabir-zheng/TCD 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.

skip_scaling Ran
ran, violated the contract we drafted
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("db077dcd1ca85df7")
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 Tensor, ndim 1, dtype family float, shape (4,) 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
import numpy as np

torch.manual_seed(0)

# Construct sigma as a small tensor
# The function performs arithmetic operations on sigma, so it needs to be a Tensor
sigma = torch.tensor([0.1, 0.5, 1.0, 2.0], dtype=torch.float32)

# sigma_data and sigma_min are float parameters with default values
sigma_data = 0.5
sigma_min = 0.002

ARGS = {
    "sigma": sigma,
    "sigma_data": sigma_data,
    "sigma_min": sigma_min,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
timesteps_schedule Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from LYMDLUT/improved_consistency_models_cifar10_pytorch
pointer only; the stored copy get_code serves, from LYMDLUT/improved_consistency_models_cifar10_pytorch, is pointer only (licence: NONE) · get_code("5d181060fa21e0cc")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

unflatten_master_params Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
openai/consistency_models/cm/fp16_util.py
pointer only (licence: MIT); the stored copy get_code serves, from ZhendongWang6/DIRE, is pointer only (licence: NONE) · get_code("64fff1e30802b815")
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 ZhendongWang6/DIRE, 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.

zero_module Ran
ran; our contract draft was wrong, not the code
openai/consistency_models/cm/nn.py
code served (permissive licence) · get_code("129b804760b3115f")
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) and returned SimpleModule. 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 simple module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 2, 3)
    
    def forward(self, x):
        return x

module = SimpleModule()

# Verify the module has non-zero parameters before zeroing
for p in module.parameters():
    assert p.abs().sum() > 0, "Parameters should be non-zero initially"

ARGS = {
    "module": module
}
Setup block drafted by
a language model, Claude Haiku 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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
AttentionBlock Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("962837b1727d71b7")
How it ran

no invocation recorded.

ConsistencyTraining Not yet run
unverified (harvested, no recorded run)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("c5b94fcc2e72016d")
How it ran

no invocation recorded.

PCMFMDeterministicScheduler Not yet run
unverified (harvested, no recorded run)
G-U-N/Phased-Consistency-Model/code/text_to_image_sd3/pcm_fm_deterministic_scheduler.py
code served (permissive licence) · get_code("6d1af0f005c519b3")
How it ran

no invocation recorded.

ResBlockShift Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("b56ce6f9b307e9e5")
How it ran

no invocation recorded.

ShiftUNet Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("b9b7422c33b745d9")
How it ran

no invocation recorded.

TimestepBlock Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("2e8d0cb0b59bdbd1")
How it ran

no invocation recorded.

TimestepEmbedSequential Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("9ce7073af820d275")
How it ran

no invocation recorded.

TimestepZBlock Not yet run
unverified (harvested, no recorded run)
sainzerjj/sferd/unet/student_unet.py
code served (permissive licence) · get_code("787099a78454d6ac")
How it ran

no invocation recorded.

avg_pool_nd Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/nn.py
code served (permissive licence) · get_code("ecd0fc28815b65ae")
How it ran

no invocation recorded.

conv_nd Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/nn.py
code served (permissive licence) · get_code("fe4eb545bbb728e0")
How it ran

no invocation recorded.

cosine_weight Not yet run
unverified (harvested, no recorded run)
crowsonkb/consistency-models/consistency_models/consistency.py
code served (permissive licence) · get_code("9b13a9bca59f4324")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

create_model Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/script_util.py
code served (permissive licence) · get_code("35ea054532112e53")
How it ran

no invocation recorded.

create_model_and_diffusion Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/script_util.py
code served (permissive licence) · get_code("7d8e408ce7ec5b07")
How it ran

no invocation recorded.

create_named_schedule_sampler Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/resample.py
code served (permissive licence) · get_code("df72d0c85cc7f5ed")
How it ran

no invocation recorded.

ema_decay_rate_schedule Not yet run
unverified (harvested, no recorded run)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("0eb7ad1d36660f2e")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

get_consistency_loss_fn Not yet run
unverified (harvested, no recorded run)
openai/consistency_models_cifar10/jcm/losses.py
code served (permissive licence) · get_code("05252c6abda35d7f")
How it ran

no invocation recorded.

get_generator Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/random_util.py
code served (permissive licence) · get_code("84423ecf52775c17")
How it ran

no invocation recorded.

get_predictor Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from yang-song/score_sde_pytorch
pointer only · get_code("a58facb8fe71823a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_sigmas_karras Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/karras_diffusion.py
pointer only (licence: MIT); the stored copy get_code serves, from guthasaibharathchandra/MAP-GA, is pointer only (licence: NONE) · get_code("00611e9feba0f93d")
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 guthasaibharathchandra/MAP-GA, 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.

improved_timesteps_schedule Not yet run
unverified (harvested, no recorded run)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("9c21b1af91813988")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

karras_sample Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/karras_diffusion.py
code served (permissive licence) · get_code("0caab2b1bad90636")
How it ran

no invocation recorded.

l2_metric Not yet run
unverified (harvested, no recorded run)
crowsonkb/consistency-models/consistency_models/consistency.py
code served (permissive licence) · get_code("78ba2ba17fe3511b")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

profile Not yet run
unverified (harvested, no recorded run)
openai/consistency_models/cm/logger.py
pointer only (licence: MIT); the stored copy get_code serves, from HeadLiuYun/NeuroDiff, is pointer only (licence: NONE) · get_code("0c6607473a4c4c55")
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 HeadLiuYun/NeuroDiff, 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.

timesteps_schedule Not yet run
unverified (harvested, no recorded run)
Kinyugo/consistency_models/consistency_models/consistency_models.py
code served (permissive licence) · get_code("0438be8b93e89bbb")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

uniform_weight Not yet run
unverified (harvested, no recorded run)
crowsonkb/consistency-models/consistency_models/consistency.py
code served (permissive licence) · get_code("841087e80145f348")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 57 samples lifted from this paper's linked repositories, 57 carry a function identity and 0 do not. Of the 56 distinct functions with an identity, 38 are also present in other papers whose code we hold (24 with at least one paper dated earlier, 17 the same month, 37 later) and 18 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
zero_module
brick of this paper's assembly: helper
196 other papers
34 dated earlier, 4 the same month, 157 later, 1 same year, order not determinable · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
normal_kl 160 other papers
27 dated earlier, 5 the same month, 126 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
approx_standard_normal_cdf 154 other papers
27 dated earlier, 5 the same month, 120 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
27 dated earlier, 5 the same month, 94 later, 2 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
conv_nd
brick of this paper's assembly: helper
121 other papers
32 dated earlier, 2 the same month, 86 later, 1 same year, order not determinable · 32 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 118 more not named here
avg_pool_nd
brick of this paper's assembly: helper
113 other papers
33 dated earlier, 2 the same month, 77 later, 1 same year, order not determinable · 31 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 110 more not named here
make_output_format 73 other papers
39 dated earlier, 2 the same month, 32 later
1611.05763 (2016-11)
Learning to reinforcement learn
1804.06459 (2018-04)
On Learning Intrinsic Rewards for Policy Gradient Methods
1806.02473 (2018-06)
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
and 70 more not named here
unflatten_master_params 72 other papers
15 dated earlier, 4 the same month, 52 later, 1 same year, order not determinable
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2112.03145 (2021-12)
Diffusion Models for Implicit Image Segmentation Ensembles
and 69 more not named here
make_master_params 70 other papers
15 dated earlier, 3 the same month, 51 later, 1 same year, order not determinable
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2112.03145 (2021-12)
Diffusion Models for Implicit Image Segmentation Ensembles
and 67 more not named here
get_param_groups_and_shapes 68 other papers
14 dated earlier, 3 the same month, 50 later, 1 same year, order not determinable
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2112.03145 (2021-12)
Diffusion Models for Implicit Image Segmentation Ensembles
and 65 more not named here
profile 61 other papers
26 dated earlier, 1 the same month, 33 later, 1 same year, order not determinable
1611.05763 (2016-11)
Learning to reinforcement learn
1905.06750 (2019-05)
Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
1906.05841 (2019-06)
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
and 58 more not named here
mpi_weighted_mean 52 other papers
18 dated earlier, 2 the same month, 31 later, 1 same year, order not determinable
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
and 49 more not named here
TimestepBlock
brick of this paper's assembly: helper
33 other papers
10 dated earlier, 2 the same month, 21 later · 28 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2112.10741 (2021-12)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
and 30 more not named here
center_crop_arr 33 other papers
8 dated earlier, 25 later
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2203.15636 (2022-03)
Diffusion Models for Counterfactual Explanations
and 30 more not named here
random_crop_arr 32 other papers
9 dated earlier, 23 later
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2203.04306 (2022-03)
Diffusion Models for Medical Anomaly Detection
and 29 more not named here
parse_resume_step_from_filename 18 other papers
4 dated earlier, 2 the same month, 12 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2205.14217 (2022-05)
Diffusion-LM Improves Controllable Text Generation
and 15 more not named here
get_predictor 16 other papers
7 dated earlier, 1 the same month, 8 later · 1 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
2112.07068 (2021-12)
Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
and 13 more not named here
register_corrector 15 other papers
7 dated earlier, 1 the same month, 7 later · 2 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2011.13456 (2020-11)
Score-Based Generative Modeling through Stochastic Differential Equations
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
and 12 more not named here
register_predictor 15 other papers
7 dated earlier, 1 the same month, 7 later · 2 only as an assembly brick
2006.09011 (2020-06)
Improved Techniques for Training Score-Based Generative Models
2011.13456 (2020-11)
Score-Based Generative Modeling through Stochastic Differential Equations
2105.14080 (2021-05)
Gotta Go Fast When Generating Data with Score-Based Models
and 12 more not named here
betas_for_alpha_bar
brick of this paper's assembly: helper
14 other papers
14 later
2311.15908 (2023-11)
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
2311.18832 (2023-11)
Exploiting Diffusion Prior for Generalizable Dense Prediction
01824 (2024 (year only))
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
and 11 more not named here

Shown: the 20 functions present in the most other papers. 18 more shared functions are not listed 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

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-ofthe-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64 ˆ64 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 64 ˆ64 and LSUN 256 ˆ256.

For agents

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

get_harvested_code_for_paper("2303.01469")
get_code_for_paper("2303.01469")
have("2303.01469")

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

curl https://syntology.ai/api/ran/2303.01469.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01469.svg)](https://syntology.ai/paper/2303.01469)

Connect an agent — have() is free.