SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.16693 · 2023

I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

20 of 29 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; 3 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 13 failures of our instrument; 9 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/2312.16693.json · badge: /api/ran/2312.16693.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
KwaiVGI/I2V-Adapter canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
bytedance/x-dyna community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/models/ip_adapter.py
pointer only (licence: NONE); the stored copy get_code serves, from rainbowluocs/openomni, is pointer only (licence: NONE) · get_code("5105747c2711b1cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

extract_local_feature_from_single_img Ran
ran on a synthesized input
bytedance/x-dyna/inference_xdyna.py
code served (permissive licence) · get_code("82ba71457fd0972f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

class MockFaceAligner:
    """Mock face aligner that detects landmarks"""
    def get_landmarks_from_image(self, img, return_landmark_score=False):
        # Return 68 facial landmarks (typical face detection)
        # Create landmarks around center of image
        h, w = img.shape[:2]
        landmarks = np.array([
            [w*0.3 + i*2, h*0.3 + (i%5)*2] for i in range(68)
        ], dtype=np.float32)
        return [landmarks]

class MockNMSProcessor:
    """Mock NMS processor for bounding box operations"""
    def compute_increased_bbox(self, bbox_land_mark, left_f=1.35, top_f=1.25, right_f=1.35, bot_f=1.45):
        left, top, right, bottom = bbox_land_mark
        center_x = (left + right) / 2
        center_y = (top + bottom) / 2
        w = right - left
        h = bottom - top
        
        new_w = w * left_f
        new_h = h * top_f
        
        new_left = int(center_x - new_w / 2)
        new_right = int(center_x + new_w / 2)
        new_top = int(center_y - new_h / 2)
        new_bottom = int(center_y + new_h / 2)
        
        return [new_left, new_top, new_right, new_bottom]

torch.manual_seed(0)

# Create a mock image (height=512, width=512, 3 channels)
img = np.random.randint(0, 256, (512, 512, 3), dtype=np.uint8)

# Create mock face aligner
fa = MockFaceAligner()

# Create mock NMS processor
nms_processor = MockNMSProcessor()

# Optional: previous bounding box and centers for fallback
last_bbox = [100, 100, 400, 450]
left_eye = np.array([200, 220], dtype=np.int32)
right_eye = np.array([300, 220], dtype=np.int32)
mouth = np.array([250, 350], dtype=np.int32)
last_center = [left_eye, right_eye, mouth]

# Optional: tensor to crop (3 channels, 512x512)
real_tocrop = torch.randn(3, 512, 512)

ARGS = {
    'img': img,
    'fa': fa,
    'nms_processor': nms_processor,
    'last_bbox': last_bbox,
    'last_center': last_center,
    'remove_local': False,
    'real_tocrop': real_tocrop
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
find_best_frame_byheadpose_fa Ran
ran on a synthesized input
bytedance/x-dyna/inference_xdyna.py
code served (permissive licence) · get_code("bf7f7ded00990ac3")
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 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 numpy as np
import cv2

class Landmarks:
    """Stand-in for a landmark detector that returns pose arrays."""
    def inference(self, image, mode=106):
        # Returns (landmarks, pose_array, other_data)
        # pose_array should be a list/array of pose values for head position
        landmarks = np.random.rand(68, 2)  # 68 facial landmarks
        pose_array = np.array([0.1, 0.2, 0.3])  # 3D head pose (pitch, yaw, roll)
        other_data = None
        return landmarks, pose_array, other_data

# Create small test images in RGB format
# source_image: single RGB image
source_image = np.random.rand(4, 5, 3).astype(np.float32)

# driving_video: list of RGB images
driving_video = [
    np.random.rand(4, 5, 3).astype(np.float32),
    np.random.rand(4, 5, 3).astype(np.float32),
    np.random.rand(4, 5, 3).astype(np.float32),
]

# Create a Landmarks instance
fa = Landmarks()

ARGS = {
    "source_image": source_image,
    "driving_video": driving_video,
    "fa": fa,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, skimage — 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
freq_mix_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KwaiVGI/I2V-Adapter/src/utils/freeinit_utils.py
pointer only (licence: NONE) · get_code("e285f4a541803f96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

gaussian_low_pass_filter Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/utils/freeinit_utils.py
pointer only (licence: NONE) · get_code("5753a1ae1b2b2a7a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
bytedance/x-dyna/animatediff/models/embeddings.py
code served (permissive licence) · get_code("45f1cb4de58b3f3d")
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 2, dtype family float, shape (18, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Define ARGS dictionary with all parameters for get_2d_sincos_pos_embed
ARGS = {
    'embed_dim': 8,
    'grid_size': 4,
    'cls_token': True,
    'extra_tokens': 2,
}
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 2, dtype family float, shape (18, 8) — shape (18, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_freq_filter Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/utils/freeinit_utils.py
pointer only (licence: NONE) · get_code("924dfd50e7486609")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bytedance/x-dyna/animatediff/models/embeddings.py
code served (permissive licence) · get_code("38f69a3d1e46016d")
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 math

torch.manual_seed(0)

ARGS = {
    "timesteps": torch.tensor([0.0, 5.0], dtype=torch.float32),
    "embedding_dim": 4,
    "flip_sin_to_cos": False,
    "downscale_freq_shift": 1.0,
    "scale": 1.0,
    "max_period": 10000,
}
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
imread_resize Ran
ran, honoured the contract we drafted
KwaiVGI/I2V-Adapter/src/utils/util.py
pointer only (licence: NONE) · get_code("e00393f9090e49e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

is_valid_image Ran
ran on a synthesized input
bytedance/x-dyna/animatediff/models/image_processor.py
code served (permissive licence) · get_code("c9903af7cf272bc4")
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 numpy as np
import PIL.Image
import torch

torch.manual_seed(0)

# Create a PIL Image
pil_image = PIL.Image.new('RGB', (4, 3))

# Create a 2D numpy array
numpy_2d = np.random.rand(4, 3)

# Create a 3D numpy array
numpy_3d = np.random.rand(4, 3, 2)

# Create a 2D torch tensor
torch_2d = torch.randn(4, 3)

# Create a 3D torch tensor
torch_3d = torch.randn(4, 3, 2)

ARGS = {
    "image": pil_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
is_valid_image_imagelist Ran
ran, violated the contract we drafted
bytedance/x-dyna/animatediff/models/image_processor.py
code served (permissive licence) · get_code("53ccc214b8346dff")
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 numpy as np
import PIL.Image
import torch

torch.manual_seed(0)

# Test case 1: 4D tensor (batch of images)
batch_tensor = torch.randn(2, 3, 4, 5)

# Test case 2: List of 3D tensors (list of images)
image_list = [torch.randn(3, 4, 5), torch.randn(3, 4, 5)]

# Test case 3: 3D numpy array (single image)
numpy_image = np.random.randn(3, 4, 5)

# Test case 4: 2D numpy array (grayscale image)
numpy_grayscale = np.random.randn(4, 5)

# Test case 5: PIL Image
pil_image = PIL.Image.new('RGB', (4, 5))

# Test case 6: List of PIL images
pil_image_list = [PIL.Image.new('RGB', (4, 5)), PIL.Image.new('RGB', (4, 5))]

# Test case 7: Mixed list of PIL and numpy images
mixed_list = [PIL.Image.new('RGB', (4, 5)), np.random.randn(3, 4, 5)]

# Test case 8: 4D numpy array (batch of images)
batch_numpy = np.random.randn(2, 3, 4, 5)

ARGS = {
    "images": batch_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
masked_mean Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/models/ip_adapter.py
pointer only (licence: NONE); the stored copy get_code serves, from Minyeol/MIDAS, is pointer only (licence: NONE) · get_code("230588e8f1237737")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

match_histogram Ran
ran, honoured the contract we drafted
KwaiVGI/I2V-Adapter/src/utils/util.py
pointer only (licence: NONE) · get_code("d8bea9099f8a52b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

renew_resnet_paths Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/utils/convert_from_ckpt.py
pointer only (licence: NONE) · get_code("dfb052a0af48540f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

renew_vae_resnet_paths Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/utils/convert_from_ckpt.py
pointer only (licence: NONE); the stored copy get_code serves, from tuananhbui89/Erasing-Adversarial-Preservation, is pointer only (licence: NONE) · get_code("c5ec9c13e456a046")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KwaiVGI/I2V-Adapter/src/models/ip_adapter.py
pointer only (licence: NONE); the stored copy get_code serves, from Minyeol/MIDAS, is pointer only (licence: NONE) · get_code("4cb2e2a2ca0bec9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

resize_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KwaiVGI/I2V-Adapter/src/utils/util.py
pointer only (licence: NONE) · get_code("2e3e408dc6b5d79d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

shave_segments Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/utils/convert_from_ckpt.py
pointer only (licence: NONE) · get_code("cea0bc82e0c96896")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

zero_module Ran
ran; our contract draft was wrong, not the code
KwaiVGI/I2V-Adapter/src/models/motion_module.py
pointer only (licence: NONE) · get_code("4719c763c53be3fe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter 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.

zero_module Ran
ran; our contract draft was wrong, not the code
bytedance/x-dyna/animatediff/models/controlnet.py
code served (permissive licence) · get_code("da94debb8019ad46")
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 SimpleModule. 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 torch import nn

torch.manual_seed(0)

# Create a simple neural network module with some parameters
class SimpleModule(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

# Instantiate the module
module = SimpleModule()

# Define the ARGS dictionary
ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
adjust_driving_video_to_src_image Not yet run
unverified (harvested, no recorded run)
bytedance/x-dyna/inference_xdyna.py
code served (permissive licence) · get_code("c8b7b26f11f30946")
How it ran

no invocation recorded.

convert_lora Not yet run
unverified (harvested, no recorded run)
KwaiVGI/I2V-Adapter/src/utils/convert_lora_safetensor_to_diffusers.py
pointer only (licence: NONE) · get_code("4e1c711f8f37a1e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

convert_motion_lora_ckpt_to_diffusers Not yet run
unverified (harvested, no recorded run)
KwaiVGI/I2V-Adapter/src/utils/convert_lora_safetensor_to_diffusers.py
pointer only (licence: NONE) · get_code("ef399950f86ca4fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
bytedance/x-dyna/animatediff/models/embeddings.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Nightmare-n/DepthAnyVideo, is pointer only (licence: NOASSERTION) · get_code("59fa7b38de05f443")
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 Nightmare-n/DepthAnyVideo, 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. No invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
KwaiVGI/I2V-Adapter/src/models/unet_blocks.py
pointer only (licence: NONE) · get_code("8b6c18061cbaa5fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
bytedance/x-dyna/animatediff/models/unet_blocks.py
code served (permissive licence) · get_code("5f11ee52e92689bd")
How it ran

no invocation recorded.

get_motion_module Not yet run
unverified (harvested, no recorded run)
bytedance/x-dyna/animatediff/models/motion_module.py
code served (permissive licence) · get_code("cd5f3777a951d27f")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
KwaiVGI/I2V-Adapter/src/models/unet_blocks.py
pointer only (licence: NONE) · get_code("07607267678d0f69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KwaiVGI/I2V-Adapter when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
bytedance/x-dyna/animatediff/models/unet_blocks.py
code served (permissive licence) · get_code("c5952d08a7df1728")
How it ran

no invocation recorded.

Also present in other papers' code

Of 29 samples lifted from this paper's linked repositories, 29 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 17 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 11 the same month, 16 later) and 12 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
zero_module 196 other papers
81 dated earlier, 9 the same month, 105 later, 1 same year, order not determinable · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
get_2d_sincos_pos_embed 69 other papers
8 dated earlier, 61 later · 12 only as an assembly brick
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
and 66 more not named here
FeedForward 47 other papers
5 dated earlier, 1 the same month, 41 later · 4 only as an assembly brick
2204.14198 (2022-04)
Flamingo: a Visual Language Model for Few-Shot Learning
2308.02463 (2023-08)
Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
and 44 more not named here
zero_module 40 other papers
8 dated earlier, 1 the same month, 31 later
2305.13077 (2023-05)
ControlVideo: Training-free Controllable Text-to-Video Generation
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
2308.03448 (2023-08)
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
and 37 more not named here
reshape_tensor 30 other papers
1 dated earlier, 1 the same month, 28 later
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2401.07519 (2024-01)
InstantID: Zero-shot Identity-Preserving Generation in Seconds
and 27 more not named here
masked_mean 18 other papers
1 dated earlier, 1 the same month, 16 later
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2404.02733 (2024-04)
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
and 15 more not named here
renew_resnet_paths 14 other papers
5 dated earlier, 1 the same month, 8 later
2307.04725 (2023-07)
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
2311.03054 (2023-11)
AnyText: Multilingual Visual Text Generation And Editing
and 11 more not named here
shave_segments 14 other papers
5 dated earlier, 1 the same month, 8 later
2307.04725 (2023-07)
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
2311.03054 (2023-11)
AnyText: Multilingual Visual Text Generation And Editing
and 11 more not named here
get_motion_module 11 other papers
2 dated earlier, 1 the same month, 8 later
2310.19512 (2023-10)
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
2311.00213 (2023-11)
Consistent Video-to-Video Transfer Using Synthetic Dataset
2312.13964 (2023-12)
PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models
and 8 more not named here
renew_vae_resnet_paths 11 other papers
4 dated earlier, 1 the same month, 6 later
2307.04725 (2023-07)
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
2311.16933 (2023-11)
SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models
and 8 more not named here
get_timestep_embedding 9 other papers
2 dated earlier, 7 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2311.16498 (2023-11)
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
2402.00769 (2024-02)
AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
and 6 more not named here
get_2d_sincos_pos_embed_from_grid 4 other papers
1 dated earlier, 3 later
2311.16498 (2023-11)
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
2405.20851 (2024-05)
MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
2408.11001 (2024-08)
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
and 1 more not named here
gaussian_low_pass_filter 3 other papers
1 the same month, 2 later
2312.07537 (2023-12)
FreeInit: Bridging Initialization Gap in Video Diffusion Models
2402.04324 (2024-02)
ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
2501.11319 (2025-01)
StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer
freq_mix_3d 2 other papers
1 the same month, 1 later
2312.07537 (2023-12)
FreeInit: Bridging Initialization Gap in Video Diffusion Models
2402.04324 (2024-02)
ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
is_valid_image_imagelist 2 other papers
2 later
2505.17013 (2025-05)
When Are Concepts Erased From Diffusion Models?
2605.15196 (2026-05)
REFDECODER: Enhancing Visual Generation with Conditional Video Decoding
convert_motion_lora_ckpt_to_diffusers 1 other paper
1 dated earlier
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
is_valid_image 1 other paper
1 later
2505.17013 (2025-05)
When Are Concepts Erased From 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

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

For agents

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

get_harvested_code_for_paper("2312.16693")
get_code_for_paper("2312.16693")
have("2312.16693")

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

curl https://syntology.ai/api/ran/2312.16693.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.16693.svg)](https://syntology.ai/paper/2312.16693)

Connect an agent — have() is free.