SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.13383 · 2024

Adversarial Diffusion Compression for Real-World Image Super-Resolution

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 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/2411.13383.json · badge: /api/ran/2411.13383.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
guaishou74851/adcsr canonical (classifier label)
classifier basis: census
10 ran · 4 no recorded run
FunctionStatusWhere it lives
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guaishou74851/adcsr/ram/models/swin_transformer.py
code served (permissive licence) · get_code("144d10b49baeb8a6")
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 Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) 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 2026-09-04T22:38:58Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using distinct sizes: 2, 8, 8, 4
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
# H=8, W=8, so window_size=4 works (8 // 4 = 2)
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
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 (8, 4, 4, 4) — shape (8, 4, 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
MyUNet2DConditionModel_SD_forward Ran
ran; our contract draft was wrong, not the code
guaishou74851/adcsr/forward.py
code served (permissive licence) · get_code("2b84a8c797f8334c")
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, 8, 8) 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)

class SimpleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1)
    
    def forward(self, x):
        return self.conv(x)

class SimpleBody(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.block = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
    
    def forward(self, x):
        return self.block(x)

class MyUNet2DConditionModel_SD(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv_in = SimpleConv(3, 4)
        self.body = SimpleBody(4)
    
    def forward(self, x):
        global skip
        x = self.conv_in(x)
        skip = [x]
        x = self.body(x)
        return x

model = MyUNet2DConditionModel_SD()
x = torch.randn(2, 3, 8, 8)

ARGS = {
    "self": model,
    "x": x
}
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, 8, 8) — shape (2, 4, 8, 8) 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
augment Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guaishou74851/adcsr/bsr/transforms.py
code served (permissive licence) · get_code("7f124cd33fb750ee")
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 tuple. 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
import cv2
import random

random.seed(0)
np.random.seed(0)

# Create sample images as ndarrays (height=4, width=3, channels=3)
img1 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Create sample flows as ndarrays (height=4, width=3, 2 channels for x,y)
flow1 = np.random.randn(4, 3, 2).astype(np.float32)
flow2 = np.random.randn(4, 3, 2).astype(np.float32)

ARGS = {
    'imgs': [img1, img2],
    'hflip': True,
    'rotation': True,
    'flows': [flow1, flow2],
    'return_status': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
find_parent Ran
ran; our contract draft was wrong, not the code
guaishou74851/adcsr/model.py
code served (permissive licence) · get_code("ce5c70c01a429c15")
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 tuple, ndim 1, 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)

# Build a small nested model with multiple levels of modules
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)

class NestedModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = SimpleModule()
        self.layer2 = nn.Linear(3, 2)

class ComplexModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.encoder = NestedModule()
        self.decoder = nn.Linear(2, 4)
        self.simple = SimpleModule()

model = ComplexModel()

# Test with a nested module name that will traverse the model hierarchy
module_name = "encoder.layer1.linear"

ARGS = {
    "model": model,
    "module_name": module_name
}
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 tuple, ndim 1, 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
mesh_grid Ran
ran; our contract draft was wrong, not the code
guaishou74851/adcsr/bsr/degradations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("794d4f7fc184e7e5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

mod_crop Ran
ran; our contract draft was wrong, not the code
guaishou74851/adcsr/bsr/transforms.py
code served (permissive licence) · get_code("223d0788b0725dfb")
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 (12, 16, 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 numpy as np

# Create a small test image (2D grayscale)
img_2d = np.random.randint(0, 256, size=(10, 15), dtype=np.uint8)

# Create a small test image (3D RGB)
img_3d = np.random.randint(0, 256, size=(12, 18, 3), dtype=np.uint8)

scale = 4

ARGS = {
    "img": img_3d,
    "scale": scale,
}
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 ndarray, ndim 3, dtype family int, shape (12, 16, 3) — shape (12, 16, 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
paired_random_crop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guaishou74851/adcsr/bsr/transforms.py
code served (permissive licence) · get_code("64cd160c586b1bef")
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 tuple. 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
import random

torch.manual_seed(0)
random.seed(0)

# Create LQ (low quality) image with dimensions (batch, channels, height, width)
# LQ size: 2x3x8x8
img_lq_tensor = torch.randn(2, 3, 8, 8)

# Create GT (ground truth) image with scale factor 2, so GT should be 2x scale larger
# GT size: 2x3x16x16 (8*2 = 16)
img_gt_tensor = torch.randn(2, 3, 16, 16)

# Alternative numpy versions for testing (not used here but shown for reference)
# img_lq_numpy = np.random.randn(8, 8, 3)
# img_gt_numpy = np.random.randn(16, 16, 3)

ARGS = {
    'img_gts': img_gt_tensor,
    'img_lqs': img_lq_tensor,
    'gt_patch_size': 8,
    'scale': 2,
    'gt_path': None,
}
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 tuple — a tuple output has no array shape of its own; none is 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
pdf2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guaishou74851/adcsr/bsr/degradations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("321b9c73d589eb9e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

sigma_matrix2 Ran
ran, honoured the contract we drafted
guaishou74851/adcsr/bsr/degradations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SHH-Han/DNF-SR, is pointer only (licence: NOASSERTION) · get_code("e3444ff2b9d24600")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SHH-Han/DNF-SR, 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.

window_reverse Ran
ran; our contract draft was wrong, not the code
guaishou74851/adcsr/ram/models/swin_transformer.py
code served (permissive licence) · get_code("61bf152e6a42a184")
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, 8, 12, 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

torch.manual_seed(0)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned from an image of size (B, H, W, C)
# where the image is divided into non-overlapping windows of size window_size x window_size

B = 2  # batch size
H = 8  # image height
W = 12  # image width
window_size = 4  # window size
C = 3  # number of channels

# Calculate number of windows
num_windows_h = H // window_size  # 2
num_windows_w = W // window_size  # 3
num_windows = num_windows_h * num_windows_w  # 6

# windows shape: (num_windows*B, window_size, window_size, C)
# = (6*2, 4, 4, 3) = (12, 4, 4, 3)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
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, 8, 12, 3) — shape (2, 8, 12, 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
MyCrossAttnDownBlock2D_SD_forward Not yet run
unverified (harvested, no recorded run)
guaishou74851/adcsr/forward.py
code served (permissive licence) · get_code("5829c1d21a42343b")
How it ran

no invocation recorded.

MyCrossAttnUpBlock2D_SD_forward Not yet run
unverified (harvested, no recorded run)
guaishou74851/adcsr/forward.py
code served (permissive licence) · get_code("2c09b61bfac07a93")
How it ran

no invocation recorded.

add_lora_to_unet Not yet run
unverified (harvested, no recorded run)
guaishou74851/adcsr/utils.py
code served (permissive licence) · get_code("969db462072820db")
How it ran

no invocation recorded.

interpolate_relative_pos_embed Not yet run
unverified (harvested, no recorded run)
guaishou74851/adcsr/ram/models/swin_transformer.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from csslc/pisa-sr, is pointer only (licence: NONE) · get_code("199b2766250bd139")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from csslc/pisa-sr, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 14 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 3 the same month, 14 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

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

FunctionAlso present inEarliest-datedOthers named
window_reverse 227 other papers
191 dated earlier, 4 the same month, 23 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
187 dated earlier, 4 the same month, 23 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
mesh_grid 8 other papers
4 dated earlier, 4 later
2310.19011 (2023-10)
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
2312.03641 (2023-12)
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
and 5 more not named here
pdf2 8 other papers
4 dated earlier, 4 later
2310.19011 (2023-10)
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
2312.03641 (2023-12)
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
and 5 more not named here
sigma_matrix2 8 other papers
4 dated earlier, 4 later
2310.19011 (2023-10)
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
2312.03641 (2023-12)
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
2403.05049 (2024-03)
XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution
and 5 more not named here
interpolate_relative_pos_embed 6 other papers
3 dated earlier, 1 the same month, 2 later
2306.02898 (2023-06)
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
2404.18253 (2024-04)
Workshop for Machine Learning for Remote Sensing (ML4RS) EFFICIENT REMOTE SENSING WITH HARMONIZED TRANSFER LEARNING AND MODALITY ALIGNMENT
2409.19961 (2024-09)
Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval
and 3 more not named here
mod_crop 3 other papers
2 dated earlier, 1 later
2305.12966 (2023-05)
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
2407.13987 (2024-07)
RealViformer: Investigating Attention for Real-World Video Super-Resolution
augment 2 other papers
1 dated earlier, 1 later
2305.12966 (2023-05)
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
paired_random_crop 2 other papers
1 dated earlier, 1 later
2305.12966 (2023-05)
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
MyCrossAttnDownBlock2D_SD_forward 1 other paper
1 later
Chen_Adversarial_Diffusion_Compression_for_Real-World_Image_Super-Resolution_CVPR_2025_paper (2025 (year only))
Adversarial Diffusion Compression for Real-World Image Super-Resolution
MyCrossAttnUpBlock2D_SD_forward 1 other paper
1 later
Chen_Adversarial_Diffusion_Compression_for_Real-World_Image_Super-Resolution_CVPR_2025_paper (2025 (year only))
Adversarial Diffusion Compression for Real-World Image Super-Resolution
MyUNet2DConditionModel_SD_forward 1 other paper
1 later
Chen_Adversarial_Diffusion_Compression_for_Real-World_Image_Super-Resolution_CVPR_2025_paper (2025 (year only))
Adversarial Diffusion Compression for Real-World Image Super-Resolution
add_lora_to_unet 1 other paper
1 later
Chen_Adversarial_Diffusion_Compression_for_Real-World_Image_Super-Resolution_CVPR_2025_paper (2025 (year only))
Adversarial Diffusion Compression for Real-World Image Super-Resolution
find_parent 1 other paper
1 later
Chen_Adversarial_Diffusion_Compression_for_Real-World_Image_Super-Resolution_CVPR_2025_paper (2025 (year only))
Adversarial Diffusion Compression for Real-World Image Super-Resolution

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

Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images from low-resolution inputs degraded by complex, unknown processes. While many Stable Diffusion (SD)-based Real-ISR methods have achieved remarkable success, their slow, multi-step inference hinders practical deployment. Recent SD-based one-step networks like OSEDiff and S3Diff alleviate this issue but still incur high computational costs due to their reliance on large pretrained SD models. This paper proposes a novel Real-ISR method, AdcSR, by distilling the one-step diffusion network OSEDiff into a streamlined diffusion-GAN model under our Adversarial Diffusion Compression (ADC) framework. We meticulously examine the modules of OSEDiff, categorizing them into two types: (1) Removable (VAE encoder, prompt extractor, text encoder, etc.) and (2) Prunable (denoising UNet and VAE decoder). Since direct removal and pruning can degrade the model's generation capability, we pretrain our pruned VAE decoder to restore its ability to decode images and employ adversarial distillation to compensate for performance loss. This ADC-based diffusion-GAN hybrid design effectively reduces complexity by 73% in inference time, 78% in computation, and 74% in parameters, while preserving the model's generation capability. Experiments manifest that our proposed AdcSR achieves competitive recovery quality on both synthetic and real-world datasets, offering up to 9.3$\times$ speedup over previous one-step diffusion-based methods. Code and models are available at https://github.com/Guaishou74851/AdcSR.

For agents

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

get_harvested_code_for_paper("2411.13383")
get_code_for_paper("2411.13383")
have("2411.13383")

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

curl https://syntology.ai/api/ran/2411.13383.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.13383.svg)](https://syntology.ai/paper/2411.13383)

Connect an agent — have() is free.