SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.09592 · ICCV · 2023

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Yan Lu, Xun Guo, Wenhao Chai, Gaoang Wang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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, 2 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/2308.09592.json · badge: /api/ran/2308.09592.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
rese1f/stablevideo canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
HWC3 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rese1f/stablevideo/annotator/util.py
code served (permissive licence) · get_code("f9ec7d70add02b6f")
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 (4, 5, 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

# Test case 1: 3-channel RGB image (most common case)
x_rgb = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8)

# Test case 2: 1-channel grayscale image
x_gray = np.random.randint(0, 256, size=(4, 5, 1), dtype=np.uint8)

# Test case 3: 4-channel RGBA image
x_rgba = np.random.randint(0, 256, size=(4, 5, 4), dtype=np.uint8)

# Test case 4: 2D image (will be expanded to 3D with 1 channel)
x_2d = np.random.randint(0, 256, size=(4, 5), dtype=np.uint8)

# Use the RGB case as the primary test
ARGS = {
    "x": x_rgb
}
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 (4, 5, 3) — shape (4, 5, 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
count_parameters Ran
ran, honoured the contract we drafted
rese1f/stablevideo/stablevideo/implicit_neural_networks.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 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
default Ran
ran, violated the contract we drafted
rese1f/stablevideo/ldm/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
exists Ran
ran, violated the contract we drafted
rese1f/stablevideo/ldm/modules/attention.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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_frames_data Ran
ran; our contract draft was wrong, not the code
rese1f/stablevideo/stablevideo/atlas_utils.py
code served (permissive licence) · get_code("265068c7d6082746")
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 torch.nn as nn

torch.manual_seed(0)

# Create a minimal config dict with all required keys
config = {
    'resx': 4,
    'resy': 3,
    'maximum_number_of_frames': 2,
    'device': 'cpu',
    'return_atlas_alpha': False,
    'grid_atlas_resolution': 8,
}

# Create minimal neural network models that satisfy the function's usage
class SimpleMapping(nn.Module):
    def __init__(self, output_dim):
        super().__init__()
        self.linear = nn.Linear(3, output_dim)
    
    def forward(self, x):
        # x shape: (num_points, 3) where 3 is (x, y, t)
        return self.linear(x)

class AlphaModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 1)
    
    def forward(self, x):
        # x shape: (num_points, 3)
        return self.linear(x)

# Instantiate the models
background_mapping = SimpleMapping(output_dim=2)
foreground_mapping = SimpleMapping(output_dim=2)
alpha_model = AlphaModel()

# Construct ARGS
ARGS = {
    'config': config,
    'foreground_mapping': foreground_mapping,
    'background_mapping': background_mapping,
    'alpha_model': alpha_model,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
scipy, torch, tqdm — 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
get_state_dict Ran
ran; our contract draft was wrong, not the code
rese1f/stablevideo/cldm/model.py
code served (permissive licence) · get_code("cfc17707f35e7ec4")
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

torch.manual_seed(0)

def get_state_dict(d):
    return d.get('state_dict', d)

# The function calls .get() on the parameter 'd', so it must be a dict-like object.
# It tries to get 'state_dict' key, and if not found, returns the dict itself.

ARGS = {
    'd': {'state_dict': {'layer1.weight': torch.randn(4, 3), 'layer1.bias': torch.randn(4)}}
}
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
load_video Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rese1f/stablevideo/stablevideo/atlas_utils.py
code served (permissive licence) · get_code("b73c0affb20bb803")
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 (5, 3, 432, 768) 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 tempfile
from PIL import Image
from pathlib import Path

torch.manual_seed(0)

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir)

# Create 5 small test images (smaller than num_frames=70 to test the slicing)
for i in range(5):
    img = Image.new('RGB', (768, 432), color=(i*50, i*50, i*50))
    img.save(temp_path / f"frame_{i:03d}.jpg")

ARGS = {
    'folder': temp_dir,
    'resize': (432, 768),
    'num_frames': 70
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — 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 (5, 3, 432, 768) — shape (5, 3, 432, 768) 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
positionalEncoding_vec Ran
ran; our contract draft was wrong, not the code
rese1f/stablevideo/stablevideo/implicit_neural_networks.py
code served (permissive licence) · get_code("ab6aff4b59ac84d5")
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 2, dtype family float, shape (2, 24) 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)

# Analyze the function:
# - in_tensor is used in einsum 'ij, k -> ijk', so it needs shape (i, j)
# - b is used in einsum 'ij, k -> ijk', so it needs shape (k,)
# - The function performs einsum, then cat on dim=1, transpose, view operations
# - All operations are tensor operations, no special methods needed

in_tensor = torch.randn(2, 3)  # batch_size=2, feature_dim=3
b = torch.randn(4)  # projection_dim=4

ARGS = {
    'in_tensor': in_tensor,
    'b': b
}
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 2, dtype family float, shape (2, 24) — shape (2, 24) 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
resize_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rese1f/stablevideo/annotator/util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from DeepakSridhar/fgdm, is pointer only (licence: NOASSERTION) · get_code("50fd68f6989503c6")
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 DeepakSridhar/fgdm, 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.

uniq Ran
ran; our contract draft was wrong, not the code
rese1f/stablevideo/ldm/modules/attention.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

load_state_dict Not yet run
unverified (harvested, no recorded run)
rese1f/stablevideo/cldm/model.py
code served (permissive licence) · get_code("df733a879693145d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 6 the same month, 8 later) and 2 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
206 dated earlier, 17 the same month, 257 later, 4 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
71 dated earlier, 9 the same month, 125 later, 2 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
count_parameters 180 other papers
96 dated earlier, 3 the same month, 77 later, 4 same year, order not determinable · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
uniq 115 other papers
30 dated earlier, 4 the same month, 79 later, 2 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_state_dict 29 other papers
6 dated earlier, 1 the same month, 22 later
2304.04269 (2023-04)
HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
2305.02034 (2023-05)
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
2305.11147 (2023-05)
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
and 26 more not named here
load_state_dict 25 other papers
6 dated earlier, 1 the same month, 18 later
2304.04269 (2023-04)
HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
2305.02034 (2023-05)
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
2305.11147 (2023-05)
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
and 22 more not named here
HWC3 18 other papers
3 dated earlier, 15 later
2305.10973 (2023-05)
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
2305.16322 (2023-05)
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
and 15 more not named here
resize_image 13 other papers
2 dated earlier, 11 later
2305.16322 (2023-05)
Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
2310.13165 (2023-10)
CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
and 10 more not named here
positionalEncoding_vec 3 other papers
3 dated earlier
2109.11418 (2021-09)
Layered Neural Atlases for Consistent Video Editing
2204.02491 (2022-04)
Text2LIVE: Text-Driven Layered Image and Video Editing
2303.08120 (2023-03)
Blind Video Deflickering by Neural Filtering with a Flawed Atlas

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

Editing results of StableVideo. The input video (top row) contains long range motion and viewpoint changing. Our approach performs stable editing according to the prompt of "Orange SUV in sunny snow winter" on foreground and background. In the edited video (bottom row), the "orange SUV" maintains high geometric and temporal consistency, although the viewpoints keep changing.

For agents

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

get_harvested_code_for_paper("2308.09592")
get_code_for_paper("2308.09592")
have("2308.09592")

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

curl https://syntology.ai/api/ran/2308.09592.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.09592.svg)](https://syntology.ai/paper/2308.09592)

Connect an agent — have() is free.