SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.17778 · NeurIPS · 2024

Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs

Zicheng Liu, Zhongdao Wang, Li Wang, Qinpeng Cui, Yixuan Liu, Xinyi Zhang, Qiqi Bao, Qingmin Liao, Tian Lu, Emad Barsoum

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 7 failures of our instrument; 1 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/2409.17778.json · badge: /api/ran/2409.17778.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
AMD-AIG-AIMA/DoSSR marked official in Papers with Code
Papers with Code archive
7 ran · 1 no recorded run
FunctionStatusWhere it lives
_extract_into_tensor Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("f36b9057d8208496")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a 1-D numpy array to extract values from
arr = np.array([0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8], dtype=np.float32)

# Create timesteps tensor with indices into the array
# batch_size = 2, so we need 2 indices
timesteps = torch.tensor([0, 3], dtype=torch.long)

# Create broadcast_shape: should have K dimensions where first dim = batch_size
# Let's use shape [2, 1, 4, 3] - batch_size=2, then 3 additional dimensions
broadcast_shape = (2, 1, 4, 3)

ARGS = {
    "arr": arr,
    "timesteps": timesteps,
    "broadcast_shape": broadcast_shape,
}
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 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
adaptive_instance_normalization Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("0a3c7e256faf29bc")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) 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 4D tensors with distinct dimensions
# Batch size: 2, Channels: 3, Height: 4, Width: 5
content_feat = torch.randn(2, 3, 4, 5)
style_feat = torch.randn(2, 3, 4, 5)

ARGS = {
    "content_feat": content_feat,
    "style_feat": style_feat,
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
calc_mean_std Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("4c8c3d07d7aa35cb")
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 tuple, ndim 5, 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

torch.manual_seed(0)

# Create a 4D tensor with shape (batch=2, channels=4, height=3, width=5)
# This satisfies the requirement that feat is a 4D tensor
feat = torch.randn(2, 4, 3, 5)

ARGS = {
    'feat': feat,
    'eps': 1e-05
}
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 tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
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
customized_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("46962bbc32b823da")
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 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 numpy as np
import torch

torch.manual_seed(0)

# Analyze the function:
# - x: used with ** operator and * operator, np.exp() - should be numeric (numpy array or similar)
# - func_type: int parameter with values 1 or 2

# Create a small numpy array for x
x = np.array([[1.0, 2.0, 3.0, 4.0],
              [0.5, 1.5, 2.5, 3.5]])

# func_type can be 1 or 2
func_type = 1

ARGS = {
    "x": x,
    "func_type": func_type
}
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 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
wavelet_blur Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("33644951e3d8dbaf")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) 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
from torch import Tensor

torch.manual_seed(0)

# Create a small image tensor with shape (batch, channels, height, width)
# Using batch=2, channels=3, height=4, width=5 for distinct dimensions
image = torch.randn(2, 3, 4, 5, dtype=torch.float32)

# radius parameter
radius = 1

ARGS = {
    "image": image,
    "radius": radius,
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
wavelet_decomposition Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("7db31c79b2da0efc")
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 tuple, ndim 5, 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
from torch import Tensor

torch.manual_seed(0)

# Create a small test image tensor
# Shape: (batch=2, channels=3, height=4, width=4)
image = torch.randn(2, 3, 4, 4, dtype=torch.float32)

# Define arguments for wavelet_decomposition
ARGS = {
    "image": image,
    "levels": 5
}
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 tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
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
wavelet_reconstruction Ran
ran; our contract draft was wrong, not the code
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("64ee5663c491414e")
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, 3, 4, 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 two small tensors for content and style features
# Shape: (batch=2, channels=3, height=4, width=4)
content_feat = torch.randn(2, 3, 4, 4, dtype=torch.float32)
style_feat = torch.randn(2, 3, 4, 4, dtype=torch.float32)

ARGS = {
    "content_feat": content_feat,
    "style_feat": style_feat,
}
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, 3, 4, 4) — shape (2, 3, 4, 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
SpacedSampler Not yet run
unverified (harvested, no recorded run)
AMD-AIG-AIMA/DoSSR/model/er_sde_sampler.py
code served (permissive licence) · get_code("54e91f4c8d0e6070")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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
calc_mean_std
brick of this paper's assembly: helper
3 other papers
3 later
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration
2412.03017 (2024-12)
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
2507.20291 (2025-07)
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training
wavelet_blur
brick of this paper's assembly: helper
1 other paper
1 later
2411.17163 (2024-11)
OSDFace: One-Step Diffusion Model for Face Restoration

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-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency and performance. Typically, they either neglect to exploit the potential of existing extensive pretrained models, limiting their generative capacity, or they necessitate a dozens of forward passes starting from random noises, compromising inference efficiency. In this paper, we present DoSSR, a Domain Shift diffusion-based SR model that capitalizes on the generative powers of pretrained diffusion models while significantly enhancing efficiency by initiating the diffusion process with low-resolution (LR) images. At the core of our approach is a domain shift equation that integrates seamlessly with existing diffusion models. This integration not only improves the use of diffusion prior but also boosts inference efficiency. Moreover, we advance our method by transitioning the discrete shift process to a continuous formulation, termed as DoS-SDEs. This advancement leads to the fast and customized solvers that further enhance sampling efficiency. Empirical results demonstrate that our proposed method achieves state-of-the-art performance on synthetic and real-world datasets, while notably requiring only 5 sampling steps. Compared to previous diffusion prior based methods, our approach achieves a remarkable speedup of 5-7 times, demonstrating its superior efficiency. Code: https://github.com/AMD-AIG-AIMA/DoSSR

For agents

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

get_harvested_code_for_paper("2409.17778")
get_code_for_paper("2409.17778")
have("2409.17778")

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

curl https://syntology.ai/api/ran/2409.17778.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.17778.svg)](https://syntology.ai/paper/2409.17778)

Connect an agent — have() is free.