SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.08889 · 2022

Lossy Compression with Gaussian Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 2 failures of our instrument; 0 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/2206.08889.json · badge: /api/ran/2206.08889.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
jeremyiv/diffc reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_noise_prediction_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jeremyiv/diffc/compress.py
code served (permissive licence) · get_code("d1f6962076902002")
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 SDXLModel. 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)

# Stand-in model classes that match the expected interface
class SD15Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

class SD21Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

class SDXLModel(nn.Module):
    def __init__(self, use_refiner=False):
        super().__init__()
        self.use_refiner = use_refiner
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

class FluxModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Mock the lib.models modules
import sys
from types import ModuleType

lib = ModuleType('lib')
lib.models = ModuleType('lib.models')
lib.models.SD15 = ModuleType('lib.models.SD15')
lib.models.SD21 = ModuleType('lib.models.SD21')
lib.models.SDXL = ModuleType('lib.models.SDXL')
lib.models.Flux = ModuleType('lib.models.Flux')

lib.models.SD15.SD15Model = SD15Model
lib.models.SD21.SD21Model = SD21Model
lib.models.SDXL.SDXLModel = SDXLModel
lib.models.Flux.FluxModel = FluxModel

sys.modules['lib'] = lib
sys.modules['lib.models'] = lib.models
sys.modules['lib.models.SD15'] = lib.models.SD15
sys.modules['lib.models.SD21'] = lib.models.SD21
sys.modules['lib.models.SDXL'] = lib.models.SDXL
sys.modules['lib.models.Flux'] = lib.models.Flux

# Create config dict
config = {
    'use_refiner': False
}

ARGS = {
    'model_name': 'SDXL',
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SDXLModel — a SDXLModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SDXLModel 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
read_diffc_file Ran
ran; our contract draft was wrong, not the code
jeremyiv/diffc/decompress.py
code served (permissive licence) · get_code("39f50c19578b56f0")
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 zlib
import struct
import tempfile
import os

# Create a temporary file with the diffc format
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.diffc')
temp_path = temp_file.name

try:
    # Prepare test data
    caption_text = "Test caption for diffc file"
    compressed_caption = zlib.compress(caption_text.encode('utf-8'))
    width = 256
    height = 128
    step_idx = 42
    image_bytes = bytes([i % 256 for i in range(1024)])  # dummy image data
    
    # Write in the format the function expects
    temp_file.write(struct.pack('<I', len(compressed_caption)))
    temp_file.write(struct.pack('<H', width))
    temp_file.write(struct.pack('<H', height))
    temp_file.write(struct.pack('<H', step_idx))
    temp_file.write(compressed_caption)
    temp_file.write(image_bytes)
    temp_file.close()
    
    ARGS = {
        'file_path': temp_path
    }
finally:
    # Clean up will happen after the function is called
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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
get_noise_prediction_model 1 other paper
1 later
2501.09815 (2025-01)
Lossy Compression with Pretrained Diffusion Models
read_diffc_file 1 other paper
1 later
2501.09815 (2025-01)
Lossy Compression with Pretrained Diffusion Models

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

We consider a novel lossy compression approach based on unconditional diffusion generative models, which we call DiffC. Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise. We implement a proof of concept and find that it works surprisingly well despite the lack of an encoder transform, outperforming the state-of-the-art generative compression method HiFiC on ImageNet 64x64. DiffC only uses a single model to encode and denoise corrupted pixels at arbitrary bitrates. The approach further provides support for progressive coding, that is, decoding from partial bit streams. We perform a rate-distortion analysis to gain a deeper understanding of its performance, providing analytical results for multivariate Gaussian data as well as theoretic bounds for general distributions. Furthermore, we prove that a flow-based reconstruction achieves a 3 dB gain over ancestral sampling at high bitrates.

For agents

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

get_harvested_code_for_paper("2206.08889")
get_code_for_paper("2206.08889")
have("2206.08889")

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

curl https://syntology.ai/api/ran/2206.08889.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.08889.svg)](https://syntology.ai/paper/2206.08889)

Connect an agent — have() is free.