SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.02148 · 2024

Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

14 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; 0 honoured the contract we drafted, 4 violated it and 0 have no contract verdict; 10 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/2404.02148.json · badge: /api/ran/2404.02148.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
fudan-zvg/diffusion-square canonical (classifier label)
classifier basis: census
11 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ali-vilab/videocomposer
pointer only · get_code("9fcdaa6e423e8aa7")
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.

default Ran
ran, violated the contract we drafted
fudan-zvg/diffusion-square/sgm/modules/attention.py
code served (permissive licence) · get_code("424012cb37b31172")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () 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.

from inspect import isfunction

def exists(val):
    return val is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

# Test case 1: val exists (not None), d is a regular value
ARGS_1 = {
    'val': 42,
    'd': 100
}

# Test case 2: val is None, d is a regular value
ARGS_2 = {
    'val': None,
    'd': 100
}

# Test case 3: val is None, d is a function
def default_func():
    return 200

ARGS_3 = {
    'val': None,
    'd': default_func
}

# Test case 4: val exists, d is a function
ARGS_4 = {
    'val': "existing_value",
    'd': lambda: "default_value"
}

# Use one of the test cases as the final ARGS
ARGS = ARGS_3
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 int, ndim 0, dtype family int, shape () — shape () 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
disabled_train Ran
ran, violated the contract we drafted
fudan-zvg/diffusion-square/sgm/util.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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 SimpleModel. 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
do_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-zvg/diffusion-square/sgm/inference/helpers.py
code served (permissive licence) · get_code("fefdc1dcee5c4986")
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, 16, 16) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import math
from omegaconf import ListConfig

torch.manual_seed(0)

# Build a minimal conditioner with embedders
class MockEmbedder(nn.Module):
    def __init__(self, input_key):
        super().__init__()
        self.input_key = input_key
    
    def forward(self, x):
        return x

class MockConditioner(nn.Module):
    def __init__(self):
        super().__init__()
        self.embedders = [
            MockEmbedder('txt'),
            MockEmbedder('original_size_as_tuple'),
        ]
    
    def get_unconditional_conditioning(self, batch, batch_uc=None, force_uc_zero_embeddings=None):
        # Return mock conditioning dicts
        c = {
            'crossattn': torch.randn(1, 8, 4),
            'concat': torch.randn(1, 4, 4, 4),
        }
        uc = {
            'crossattn': torch.randn(1, 8, 4),
            'concat': torch.randn(1, 4, 4, 4),
        }
        return c, uc

# Build a minimal model
class MockDenoiser(nn.Module):
    def __init__(self):
        super().__init__()
    
    def __call__(self, model, input, sigma, c, **kwargs):
        return torch.randn_like(input)

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conditioner = MockConditioner()
        self.denoiser = MockDenoiser()
        self.inner_model = nn.Linear(4, 4)
        self.model = self.inner_model
        self._ema_scope_entered = False
    
    def decode_first_stage(self, z):
        # Decode latents to image space
        return torch.randn(z.shape[0], 3, 16, 16)
    
    def ema_scope(self):
        return self
    
    def __enter__(self):
        return self
    
    def __exit__(self, *args):
        pass

# Build a minimal sampler
def mock_sampler(denoiser, randn, cond=None, uc=None):
    return torch.randn_like(randn)

# Build value_dict
value_dict = {
    'prompt': 'a test prompt',
    'negative_prompt': 'negative test prompt',
    'orig_height': 512,
    'orig_width': 768,
    'crop_coords_top': 0,
    'crop_coords_left': 0,
    'aesthetic_score': 7.5,
    'negative_aesthetic_score': 2.5,
    'target_height': 512,
    'target_width': 768,
}

ARGS = {
    'model': MockModel(),
    'sampler': mock_sampler,
    'value_dict': value_dict,
    'num_samples': 2,
    'H': 64,
    'W': 96,
    'C': 4,
    'F': 8,
    'force_uc_zero_embeddings': None,
    'batch2model_input': [],
    'return_latents': False,
    'filter': None,
    'device': 'cpu',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, omegaconf, 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, 16, 16) — shape (2, 3, 16, 16) 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
exists Ran
ran, violated the contract we drafted
fudan-zvg/diffusion-square/sgm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-zvg/diffusion-square/sgm/inference/helpers.py
code served (permissive licence) · get_code("c52b1e32cdda91f9")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 math
from typing import List, Union
import numpy as np
import torch
from omegaconf import ListConfig

torch.manual_seed(0)

keys = ['txt', 'original_size_as_tuple', 'crop_coords_top_left', 'aesthetic_score', 'target_size_as_tuple']

value_dict = {
    'prompt': 'a beautiful landscape',
    'negative_prompt': 'ugly, blurry',
    'orig_height': 768,
    'orig_width': 512,
    'crop_coords_top': 10,
    'crop_coords_left': 20,
    'aesthetic_score': 0.8,
    'negative_aesthetic_score': 0.2,
    'target_height': 1024,
    'target_width': 768,
}

N = [2, 3]

ARGS = {
    'keys': keys,
    'value_dict': value_dict,
    'N': N,
    'device': 'cpu',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, omegaconf, 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
get_discretization_config Ran
ran; our contract draft was wrong, not the code
fudan-zvg/diffusion-square/sgm/inference/api.py
code served (permissive licence) · get_code("327b8b8283ecfd73")
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 dict. 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 dataclasses import asdict, dataclass
from enum import Enum

class Sampler(str, Enum):
    EULER_EDM = 'EulerEDMSampler'
    HEUN_EDM = 'HeunEDMSampler'
    EULER_ANCESTRAL = 'EulerAncestralSampler'
    DPMPP2S_ANCESTRAL = 'DPMPP2SAncestralSampler'
    DPMPP2M = 'DPMPP2MSampler'
    LINEAR_MULTISTEP = 'LinearMultistepSampler'

class Discretization(str, Enum):
    LEGACY_DDPM = 'LegacyDDPMDiscretization'
    EDM = 'EDMDiscretization'

class Guider(str, Enum):
    VANILLA = 'VanillaCFG'
    IDENTITY = 'IdentityGuider'

class Thresholder(str, Enum):
    NONE = 'None'

@dataclass
class SamplingParams:
    width: int = 1024
    height: int = 1024
    steps: int = 50
    sampler: Sampler = Sampler.DPMPP2M
    discretization: Discretization = Discretization.LEGACY_DDPM
    guider: Guider = Guider.VANILLA
    thresholder: Thresholder = Thresholder.NONE
    scale: float = 6.0
    aesthetic_score: float = 5.0
    negative_aesthetic_score: float = 5.0
    img2img_strength: float = 1.0
    orig_width: int = 1024
    orig_height: int = 1024
    crop_coords_top: int = 0
    crop_coords_left: int = 0
    sigma_min: float = 0.0292
    sigma_max: float = 14.6146
    rho: float = 3.0
    s_churn: float = 0.0
    s_tmin: float = 0.0
    s_tmax: float = 999.0
    s_noise: float = 1.0
    eta: float = 1.0
    order: int = 4

torch.manual_seed(0)

# Create test instances with different discretization types
params_legacy = SamplingParams(
    width=512,
    height=512,
    steps=25,
    discretization=Discretization.LEGACY_DDPM
)

params_edm = SamplingParams(
    width=512,
    height=512,
    steps=25,
    discretization=Discretization.EDM,
    sigma_min=0.1,
    sigma_max=15.0,
    rho=2.5
)

ARGS = {
    'params': params_legacy
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_guider_config Ran
ran; our contract draft was wrong, not the code
fudan-zvg/diffusion-square/sgm/inference/api.py
code served (permissive licence) · get_code("f89b6fdf331885c2")
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 dict. 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 asdict, dataclass
from enum import Enum

class Sampler(str, Enum):
    EULER_EDM = 'EulerEDMSampler'
    HEUN_EDM = 'HeunEDMSampler'
    EULER_ANCESTRAL = 'EulerAncestralSampler'
    DPMPP2S_ANCESTRAL = 'DPMPP2SAncestralSampler'
    DPMPP2M = 'DPMPP2MSampler'
    LINEAR_MULTISTEP = 'LinearMultistepSampler'

class Discretization(str, Enum):
    LEGACY_DDPM = 'LegacyDDPMDiscretization'
    EDM = 'EDMDiscretization'

class Guider(str, Enum):
    VANILLA = 'VanillaCFG'
    IDENTITY = 'IdentityGuider'

class Thresholder(str, Enum):
    NONE = 'None'

@dataclass
class SamplingParams:
    width: int = 1024
    height: int = 1024
    steps: int = 50
    sampler: Sampler = Sampler.DPMPP2M
    discretization: Discretization = Discretization.LEGACY_DDPM
    guider: Guider = Guider.VANILLA
    thresholder: Thresholder = Thresholder.NONE
    scale: float = 6.0
    aesthetic_score: float = 5.0
    negative_aesthetic_score: float = 5.0
    img2img_strength: float = 1.0
    orig_width: int = 1024
    orig_height: int = 1024
    crop_coords_top: int = 0
    crop_coords_left: int = 0
    sigma_min: float = 0.0292
    sigma_max: float = 14.6146
    rho: float = 3.0
    s_churn: float = 0.0
    s_tmin: float = 0.0
    s_tmax: float = 999.0
    s_noise: float = 1.0
    eta: float = 1.0
    order: int = 4

torch.manual_seed(0)

params_vanilla = SamplingParams(
    width=512,
    height=512,
    steps=25,
    sampler=Sampler.DPMPP2M,
    discretization=Discretization.LEGACY_DDPM,
    guider=Guider.VANILLA,
    thresholder=Thresholder.NONE,
    scale=7.5,
    aesthetic_score=6.0,
    negative_aesthetic_score=4.0,
    img2img_strength=0.8,
    orig_width=512,
    orig_height=512,
    crop_coords_top=0,
    crop_coords_left=0,
    sigma_min=0.0292,
    sigma_max=14.6146,
    rho=3.0,
    s_churn=0.1,
    s_tmin=0.0,
    s_tmax=999.0,
    s_noise=1.0,
    eta=0.5,
    order=4
)

params_identity = SamplingParams(
    width=256,
    height=256,
    steps=20,
    sampler=Sampler.EULER_EDM,
    discretization=Discretization.EDM,
    guider=Guider.IDENTITY,
    thresholder=Thresholder.NONE,
    scale=1.0,
)

ARGS = {
    'params': params_vanilla
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_string_from_tuple Ran
ran; our contract draft was wrong, not the code
fudan-zvg/diffusion-square/sgm/util.py
code served (permissive licence) · get_code("2036522d462af205")
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 str. 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

def get_string_from_tuple(s):
    try:
        if s[0] == '(' and s[-1] == ')':
            t = eval(s)
            if type(t) == tuple:
                return t[0]
            else:
                pass
    except:
        pass
    return s

# The function takes a string parameter and checks if it's a string representation
# of a tuple, evaluates it, and returns the first element if it is a tuple.
# Otherwise it returns the input string unchanged.

ARGS = {
    "s": "('hello', 'world')"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from morganstanley/msml
pointer only · get_code("cb49209c125de1b4")
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.

get_unique_embedder_keys_from_conditioner Ran
ran; our contract draft was wrong, not the code
fudan-zvg/diffusion-square/sgm/inference/helpers.py
code served (permissive licence) · get_code("6686c8acf02ec831")
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 list, 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)

# The function accesses conditioner.embedders and iterates over it,
# accessing the input_key attribute of each embedder.
# We need to build a minimal conditioner object with embedders that have input_key attributes.

class DummyEmbedder(nn.Module):
    def __init__(self, input_key):
        super().__init__()
        self.input_key = input_key
    
    def forward(self, x):
        return x

class DummyConditioner(nn.Module):
    def __init__(self, embedders):
        super().__init__()
        self.embedders = embedders
    
    def forward(self, x):
        return x

# Create some dummy embedders with different input_keys
embedder1 = DummyEmbedder("text")
embedder2 = DummyEmbedder("image")
embedder3 = DummyEmbedder("text")  # Duplicate key to test uniqueness

# Create the conditioner with these embedders
conditioner = DummyConditioner([embedder1, embedder2, embedder3])

ARGS = {
    "conditioner": conditioner
}
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 list, ndim 1, dtype family float — a list 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
is_power_of_two Ran
ran, violated the contract we drafted
fudan-zvg/diffusion-square/sgm/util.py
code served (permissive licence) · get_code("3753e92206c00bb9")
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 bool, ndim 0, dtype family float, shape () 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

# The function is_power_of_two takes a single integer parameter n
# It checks if n is a power of 2 using bitwise operations
# We need to provide valid integer arguments to test the function

ARGS = {
    "n": 8  # 8 is 2^3, so this should return True
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from morganstanley/msml
pointer only · get_code("3137073275f8c21a")
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.

uniq Ran
ran; our contract draft was wrong, not the code
fudan-zvg/diffusion-square/sgm/modules/attention.py
pointer only (licence: MIT); the stored copy get_code serves, from JingWu321/MUNBa, is pointer only (licence: NONE) · get_code("9a299fe5ae09e407")
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 JingWu321/MUNBa, 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.

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 (14 with at least one paper dated earlier, 7 the same month, 8 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
exists 486 other papers
329 dated earlier, 6 the same month, 140 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 207 other papers
140 dated earlier, 4 the same month, 57 later, 6 same year, order not determinable · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
disabled_train 173 other papers
96 dated earlier, 7 the same month, 62 later, 8 same year, order not determinable · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
nonlinearity 156 other papers
73 dated earlier, 3 the same month, 76 later, 4 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
uniq 115 other papers
74 dated earlier, 2 the same month, 35 later, 4 same year, order not determinable
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2206.02779 (2022-06)
Blended Latent Diffusion
and 112 more not named here
get_timestep_embedding 91 other papers
54 dated earlier, 2 the same month, 31 later, 4 same year, order not determinable · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
Normalize 54 other papers
19 dated earlier, 3 the same month, 31 later, 1 same year, order not determinable · 3 only as an assembly brick
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2208.13753 (2022-08)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
2211.13221 (2022-11)
Latent Video Diffusion Models for High-Fidelity Long Video Generation
and 51 more not named here
get_string_from_tuple 4 other papers
3 dated earlier, 1 same year, order not determinable
2311.16813 (2023-11)
Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
2312.06573 (2023-12)
ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems
04534 (2024 (year only))
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
and 1 more not named here
is_power_of_two 4 other papers
3 dated earlier, 1 same year, order not determinable
2311.16813 (2023-11)
Panacea: Panoramic and Controllable Video Generation for Autonomous Driving
2312.06573 (2023-12)
ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems
04534 (2024 (year only))
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
and 1 more not named here
get_unique_embedder_keys_from_conditioner 2 other papers
1 dated earlier, 1 later
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
2502.05179 (2025-02)
FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
do_sample 1 other paper
1 dated earlier
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
get_batch 1 other paper
1 dated earlier
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
get_discretization_config 1 other paper
1 dated earlier
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
get_guider_config 1 other paper
1 dated earlier
2403.11207 (2024-03)
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

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

Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images. However, due to the scarcity of synchronized multi-view video data, it remains challenging to adapt this paradigm to 4D generation directly. Despite that, the available video and 3D data are adequate for training video and multi-view diffusion models separately that can provide satisfactory dynamic and geometric priors respectively. To take advantage of both, this paper presents Diffusion$^2$, a novel framework for dynamic 3D content creation that reconciles the knowledge about geometric consistency and temporal smoothness from these models to directly sample dense multi-view multi-frame images which can be employed to optimize continuous 4D representation. Specifically, we design a simple yet effective denoising strategy via score composition of pretrained video and multi-view diffusion models based on the probability structure of the target image array. To alleviate the potential conflicts between two heterogeneous scores, we further introduce variance-reducing sampling via interpolated steps, facilitating smooth and stable generation. Owing to the high parallelism of the proposed image generation process and the efficiency of the modern 4D reconstruction pipeline, our framework can generate 4D content within few minutes. Notably, our method circumvents the reliance on expensive and hard-to-scale 4D data, thereby having the potential to benefit from the scaling of the foundation video and multi-view diffusion models. Extensive experiments demonstrate the efficacy of our proposed framework in generating highly seamless and consistent 4D assets under various types of conditions.

For agents

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

get_harvested_code_for_paper("2404.02148")
get_code_for_paper("2404.02148")
have("2404.02148")

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

curl https://syntology.ai/api/ran/2404.02148.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.02148.svg)](https://syntology.ai/paper/2404.02148)

Connect an agent — have() is free.