SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08382 · ICLR · 2023

Dual Diffusion Implicit Bridges for Image-to-Image Translation

Chenlin Meng, Stefano Ermon, Jiaming Song, Xuan Su

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 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/2203.08382.json · badge: /api/ran/2203.08382.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
suxuann/ddib canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
GaussianDiffusion Ran
ran on a synthesized input · constructed an object; no result was computed
suxuann/ddib/guided_diffusion/respace.py
code served (permissive licence) · get_code("1dba99f1bde1883b")
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, GaussianDiffusion: 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 numpy as np
from enum import auto

torch.manual_seed(0)

# Define the enums locally for reference
class LossType:
    MSE = "MSE"
    RESCALED_MSE = "RESCALED_MSE"
    KL = "KL"
    RESCALED_KL = "RESCALED_KL"

class ModelMeanType:
    PREVIOUS_X = "PREVIOUS_X"
    START_X = "START_X"
    EPSILON = "EPSILON"

class ModelVarType:
    LEARNED = "LEARNED"
    FIXED_SMALL = "FIXED_SMALL"
    FIXED_LARGE = "FIXED_LARGE"
    LEARNED_RANGE = "LEARNED_RANGE"

# Create a valid betas array
# betas must be 1-D, positive, and less than 1
num_timesteps = 1000
betas = np.linspace(0.0001, 0.02, num_timesteps, dtype=np.float64)

ARGS = {
    "betas": betas,
    "model_mean_type": ModelMeanType.EPSILON,
    "model_var_type": ModelVarType.FIXED_LARGE,
    "loss_type": LossType.MSE,
    "rescale_timesteps": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GaussianDiffusion — 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 GaussianDiffusion 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
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
suxuann/ddib/guided_diffusion/gaussian_diffusion.py
code served (permissive licence) · get_code("809d6a4eb92a37c4")
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 ndarray, 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 numpy as np
import math

# Define a simple alpha_bar function that follows a cosine schedule
def alpha_bar_fn(t):
    """
    Cosine annealing schedule for alpha_bar.
    Returns the cumulative product of (1-beta) at time t in [0,1].
    """
    s = 0.008
    return math.cos(((t + s) / (1 + s)) * math.pi * 0.5) ** 2

ARGS = {
    "num_diffusion_timesteps": 10,
    "alpha_bar": alpha_bar_fn,
    "max_beta": 0.999,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, 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
SpacedDiffusion Not yet run
unverified (harvested, no recorded run)
suxuann/ddib/guided_diffusion/respace.py
code served (permissive licence) · get_code("8909f9c9217a637e")
How it ran

no invocation recorded.

get_named_beta_schedule Not yet run
unverified (harvested, no recorded run)
suxuann/ddib/guided_diffusion/gaussian_diffusion.py
code served (permissive licence) · get_code("3dfd61c7077a1607")
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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 3 later) and 1 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
betas_for_alpha_bar 92 other papers
7 dated earlier, 1 the same month, 84 later · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
and 89 more not named here
get_named_beta_schedule 63 other papers
5 dated earlier, 2 the same month, 56 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2108.02938 (2021-08)
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 60 more not named here
SpacedDiffusion
brick of this paper's assembly: entry
7 other papers
2 dated earlier, 5 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2202.00512 (2022-02)
PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS
2310.11320 (2023-10)
Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
and 4 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

Common image-to-image translation methods rely on joint training over data from both source and target domains. The training process requires concurrent access to both datasets, which hinders data separation and privacy protection; and existing models cannot be easily adapted for translation of new domain pairs. We present Dual Diffusion Implicit Bridges (DDIBs), an image translation method based on diffusion models, that circumvents training on domain pairs. Image translation with DDIBs relies on two diffusion models trained independently on each domain, and is a two-step process: DDIBs first obtain latent encodings for source images with the source diffusion model, and then decode such encodings using the target model to construct target images. Both steps are defined via ordinary differential equations (ODEs), thus the process is cycle consistent only up to discretization errors of the ODE solvers. Theoretically, we interpret DDIBs as concatenation of source to latent, and latent to target Schrödinger Bridges, a form of entropy-regularized optimal transport, to explain the efficacy of the method. Experimentally, we apply DDIBs on synthetic and high-resolution image datasets, to demonstrate their utility in a wide variety of translation tasks and their inherent optimal transport properties.

For agents

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

get_harvested_code_for_paper("2203.08382")
get_code_for_paper("2203.08382")
have("2203.08382")

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

curl https://syntology.ai/api/ran/2203.08382.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.08382.svg)](https://syntology.ai/paper/2203.08382)

Connect an agent — have() is free.