SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.04324 · 2024

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 8 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/2402.04324.json · badge: /api/ran/2402.04324.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
TIGER-AI-Lab/ConsistI2V canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
broadcat Ran
ran, honoured the contract we drafted
TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.py
code served (permissive licence) · get_code("f07bf3d46feead4c")
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, 12) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

# The function broadcat takes a list of tensors and an optional dim parameter
# It broadcasts them together and concatenates along the specified dimension

# Create small tensors with distinct sizes for different dimensions
tensor1 = torch.randn(2, 4)  # batch=2, features=4
tensor2 = torch.randn(2, 1)  # batch=2, features=1 (different feature size to test broadcasting)
tensor3 = torch.randn(1, 4)  # batch=1, features=4 (different batch size to test broadcasting)

tensors = [tensor1, tensor2, tensor3]
dim = -1

ARGS = {
    "tensors": tensors,
    "dim": dim,
}
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, 12) — shape (2, 12) 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
TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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.

exists Ran
ran, violated the contract we drafted
TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.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.

freq_mix_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py
code served (permissive licence) · get_code("e285f4a541803f96")
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, 4, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.fft as fft

torch.manual_seed(0)

# Create small 3D tensors for x and noise
# Shape: (batch=2, depth=4, height=3, width=5) to have distinct dimensions
x = torch.randn(2, 4, 3, 5)
noise = torch.randn(2, 4, 3, 5)

# Create a low pass filter with the same spatial dimensions as x and noise
# LPF should be broadcastable to the frequency domain tensors
# Shape: (1, 4, 3, 5) - same as last 3 dims of x/noise
LPF = torch.ones(1, 4, 3, 5) * 0.5  # 0.5 acts as a simple low-pass filter

ARGS = {
    "x": x,
    "noise": noise,
    "LPF": LPF,
}
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, 4, 3, 5) — shape (2, 4, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian_low_pass_filter Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py
code served (permissive licence) · get_code("5753a1ae1b2b2a7a")
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 5, dtype family float, shape (2, 3, 4, 5, 6) 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 math

torch.manual_seed(0)

# The function expects:
# - shape: a tuple/list representing the shape of a filter volume
# - d_s: normalized stop frequency for spatial dimensions (float, 0.0-1.0)
# - d_t: normalized stop frequency for temporal dimension (float, 0.0-1.0)

# Looking at the function body:
# - It accesses shape[-3], shape[-2], shape[-1] for T, H, W
# - It creates a torch.zeros(shape) tensor
# - It iterates through t, h, w ranges and indexes mask[..., t, h, w]
# - d_s and d_t are used in arithmetic operations

# Create a small 5D shape (batch, channels, time, height, width)
shape = (2, 3, 4, 5, 6)

# Set d_s and d_t to valid normalized frequencies
d_s = 0.25
d_t = 0.25

ARGS = {
    "shape": shape,
    "d_s": d_s,
    "d_t": d_t,
}
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 5, dtype family float, shape (2, 3, 4, 5, 6) — shape (2, 3, 4, 5, 6) 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
get_freq_filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py
code served (permissive licence) · get_code("e6e9076eaee4d40e")
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 5, dtype family float, shape (2, 4, 3, 5, 6) 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 math

torch.manual_seed(0)

# Define arguments for get_freq_filter function
ARGS = {
    'shape': (2, 4, 3, 5, 6),  # (B, C, T, H, W) - batch=2, channels=4, temporal=3, height=5, width=6
    'device': torch.device('cpu'),
    'filter_type': 'gaussian',
    'n': 4,
    'd_s': 0.25,
    'd_t': 0.25,
}
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 5, dtype family float, shape (2, 4, 3, 5, 6) — shape (2, 4, 3, 5, 6) 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
get_noise_pred_single Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py
code served (permissive licence) · get_code("5c98cd544c2fe28d")
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, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal UNet mock that accepts the expected parameters
class MockUNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, latents, t, encoder_hidden_states, first_frame_latents, frame_stride):
        # Mock unet just processes latents and returns output with .sample attribute
        batch_size = latents.shape[0]
        noise = self.linear(latents.reshape(batch_size, -1))
        noise = noise.reshape_as(latents)
        
        # Wrap in a simple object with .sample attribute
        class Output:
            def __init__(self, sample):
                self.sample = sample
        
        return Output(noise)

# Create tiny tensors with distinct dimensions
batch_size = 2
latent_dim = 4
context_dim = 3
first_frame_latent_dim = 4

latents = torch.randn(batch_size, latent_dim)
t = torch.tensor([0, 50])
context = torch.randn(batch_size, 5, context_dim)  # (batch, seq_len, hidden_dim)
first_frame_latents = torch.randn(batch_size, first_frame_latent_dim)
frame_stride = 1
unet = MockUNet()

ARGS = {
    "latents": latents,
    "t": t,
    "context": context,
    "first_frame_latents": first_frame_latents,
    "frame_stride": frame_stride,
    "unet": unet
}
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, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
next_step Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py
code served (permissive licence) · get_code("fb032d6fa7e6196d")
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, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

class DDIMSchedulerConfig:
    def __init__(self):
        self.num_train_timesteps = 1000

class DDIMScheduler:
    def __init__(self):
        self.config = DDIMSchedulerConfig()
        self.num_inference_steps = 50
        # Create alphas_cumprod with 1000 timesteps
        self.alphas_cumprod = torch.linspace(0.9999, 0.0001, 1000)
        self.final_alpha_cumprod = torch.tensor(0.0)

model_output = torch.randn(2, 4)
timestep = 500
sample = torch.randn(2, 4)
ddim_scheduler = DDIMScheduler()

ARGS = {
    "model_output": model_output,
    "timestep": timestep,
    "sample": sample,
    "ddim_scheduler": ddim_scheduler
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pan_left Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_conditional_animation.py
code served (permissive licence) · get_code("6a8efc5f6a39c807")
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 (16, 3, 512, 256) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torchvision.transforms import functional as F

torch.manual_seed(0)

# Create a small test image tensor
# Shape: (C, H, W) where C=3 (RGB), H=512, W=512
# This gives us enough width to crop from
image = torch.randint(0, 256, (3, 512, 512), dtype=torch.uint8).float()

ARGS = {
    "image": image,
    "num_frames": 16,
    "crop_width": 256,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 (16, 3, 512, 256) — shape (16, 3, 512, 256) 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
pan_right Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_conditional_animation.py
code served (permissive licence) · get_code("b2e8efa1d185957b")
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 int, shape (16, 3, 128, 256) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torchvision.transforms import functional as F

torch.manual_seed(0)

# Create a small test image tensor
# Shape: (C, H, W) where C=3 (RGB), H=128, W=512
# We need width > crop_width for the function to work properly
image = torch.randint(0, 256, (3, 128, 512), dtype=torch.uint8)

ARGS = {
    "image": image,
    "num_frames": 16,
    "crop_width": 256,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 int, shape (16, 3, 128, 256) — shape (16, 3, 128, 256) 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
rescale_noise_cfg Ran
ran; our contract draft was wrong, not the code
TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_autoregress_animation.py
code served (permissive licence) · get_code("bea2d776a332f2b0")
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, 4, 3, 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)

# Create small tensors with distinct dimensions
# noise_cfg: shape (batch=2, channels=4, height=3, width=3)
noise_cfg = torch.randn(2, 4, 3, 3)

# noise_pred_text: shape (batch=2, channels=4, height=3, width=3)
noise_pred_text = torch.randn(2, 4, 3, 3)

# guidance_rescale: float between 0 and 1
guidance_rescale = 0.7

ARGS = {
    "noise_cfg": noise_cfg,
    "noise_pred_text": noise_pred_text,
    "guidance_rescale": guidance_rescale,
}
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, 4, 3, 3) — shape (2, 4, 3, 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
init_prompt Not yet run
unverified (harvested, no recorded run)
TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py
code served (permissive licence) · get_code("a0a4d94af120c56f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 5 the same month, 5 later) and 3 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
293 dated earlier, 15 the same month, 167 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 163 other papers
113 dated earlier, 6 the same month, 41 later, 2 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
rescale_noise_cfg 62 other papers
14 dated earlier, 2 the same month, 45 later, 1 same year, order not determinable
2206.02779 (2022-06)
Blended Latent Diffusion
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2309.06380 (2023-09)
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
and 59 more not named here
init_prompt 14 other papers
13 dated earlier, 1 the same month
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
and 11 more not named here
next_step 11 other papers
10 dated earlier, 1 the same month
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
and 8 more not named here
broadcat 4 other papers
1 dated earlier, 3 later
2212.10554 (2022-12)
A Length-Extrapolatable Transformer
2504.13181 (2025-04)
Perception Encoder: The best visual embeddings are not at the output of the network
2506.08297 (2025-06)
SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging
and 1 more not named here
gaussian_low_pass_filter 3 other papers
2 dated earlier, 1 later
2312.07537 (2023-12)
FreeInit: Bridging Initialization Gap in Video Diffusion Models
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
2501.11319 (2025-01)
StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer
freq_mix_3d 2 other papers
2 dated earlier
2312.07537 (2023-12)
FreeInit: Bridging Initialization Gap in Video Diffusion Models
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
get_freq_filter 1 other paper
1 dated earlier
2312.07537 (2023-12)
FreeInit: Bridging Initialization Gap in Video 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

Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first frame to maintain spatial and motion consistency, (2) noise initialization from the low-frequency band of the first frame to enhance layout consistency. These two approaches enable ConsistI2V to generate highly consistent videos. We also extend the proposed approaches to show their potential to improve consistency in auto-regressive long video generation and camera motion control. To verify the effectiveness of our method, we propose I2V-Bench, a comprehensive evaluation benchmark for I2V generation. Our automatic and human evaluation results demonstrate the superiority of ConsistI2V over existing methods.

For agents

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

get_harvested_code_for_paper("2402.04324")
get_code_for_paper("2402.04324")
have("2402.04324")

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

curl https://syntology.ai/api/ran/2402.04324.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.04324.svg)](https://syntology.ai/paper/2402.04324)

Connect an agent — have() is free.