SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.01790 · 2025

Ingredients: Blending Custom Photos with Video Diffusion Transformers

arXiv · PDF · Open in the Atlas

Code that ran

14 of 22 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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 9 failures of our instrument; 8 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/2501.01790.json · badge: /api/ran/2501.01790.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
feizc/ingredients canonical (classifier label)
classifier basis not recorded on the link
14 ran · 8 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/models/local_facial_extractor.py
pointer only (licence: Apache-2.0); 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: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from rainbowluocs/openomni, 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.

compute_prompt_embeddings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feizc/ingredients/models/utils.py
code served (permissive licence) · get_code("025423ed7b216773")
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 3, dtype family float, shape (1, 226, 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
from transformers import T5EncoderModel, T5Tokenizer

torch.manual_seed(0)

# Create a minimal mock tokenizer
class MockTokenizer:
    def __call__(self, prompts, padding=None, max_length=None, truncation=None, add_special_tokens=None, return_tensors=None):
        batch_size = len(prompts) if isinstance(prompts, list) else 1
        # Return a mock tokenizer output with input_ids
        class TokenizerOutput:
            def __init__(self, input_ids):
                self.input_ids = input_ids
        
        input_ids = torch.randint(0, 100, (batch_size, max_length))
        return TokenizerOutput(input_ids)

# Create a minimal mock text encoder
class MockTextEncoder(nn.Module):
    def __init__(self, hidden_size=4):
        super().__init__()
        self.hidden_size = hidden_size
        self.embedding = nn.Embedding(100, hidden_size)
    
    def forward(self, input_ids):
        # Return tuple where first element is embeddings
        embeddings = self.embedding(input_ids)
        return (embeddings,)

tokenizer = MockTokenizer()
text_encoder = MockTextEncoder(hidden_size=4)
device = torch.device('cpu')
dtype = torch.float32

prompt = "a cat sitting on a mat"
max_sequence_length = 226

ARGS = {
    "tokenizer": tokenizer,
    "text_encoder": text_encoder,
    "prompt": prompt,
    "max_sequence_length": max_sequence_length,
    "device": device,
    "dtype": dtype,
    "requires_grad": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (1, 226, 4) — shape (1, 226, 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/metric/curricularface/model_resnet.py
code served (permissive licence) · get_code("85a6d411e524efe4")
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 Conv2d. 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.nn import Conv2d

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/metric/curricularface/model_resnet.py
code served (permissive licence) · get_code("6ccc5338f47a440c")
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 Conv2d. 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.nn import Conv2d

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
draw_kps Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/models/pipeline_ingredients.py
code served (permissive licence) · get_code("4ccfaec71f6cfcc8")
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 Image. 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
from PIL import Image

# Create a small test image
width, height = 100, 80
image_array = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
image_pil = Image.fromarray(image_array)

# Create keypoints array: 5 keypoints (matching limbSeq indices 0-4), each with (x, y) coordinates
kps = np.array([
    [20, 30],    # keypoint 0
    [40, 35],    # keypoint 1
    [50, 50],    # keypoint 2
    [60, 40],    # keypoint 3
    [70, 55]     # keypoint 4
], dtype=np.float32)

# Default color list is already provided in function signature
color_list = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255)]

ARGS = {
    "image_pil": image_pil,
    "kps": kps,
    "color_list": color_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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_block Ran
ran, honoured the contract we drafted
feizc/ingredients/metric/curricularface/model_irse.py
code served (permissive licence) · get_code("ad5dbf57f3ea2633")
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 list, ndim 2, dtype family int; 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
from collections import namedtuple

torch.manual_seed(0)

# The function get_block takes in_channel, depth, num_units, and stride
# It returns a list of Bottleneck namedtuples

ARGS = {
    'in_channel': 64,
    'depth': 128,
    'num_units': 3,
    'stride': 2
}
Setup block drafted by
a language model, Claude Sonnet 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 list, ndim 2, dtype family int — 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
get_blocks Ran
ran, honoured the contract we drafted
feizc/ingredients/metric/curricularface/model_irse.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Armxyz1/Results-on-RFW, is pointer only (licence: NONE) · get_code("e82dfb7d2386721b")
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 Armxyz1/Results-on-RFW, 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_face_keypoints Ran
ran on a synthesized input
feizc/ingredients/metric/face_sim_fid.py
code served (permissive licence) · get_code("e185497b8158057e")
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 torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The function calls face_model.get(image_bgr)
# It expects the result to be a list of dicts, each with a 'bbox' key
# Each bbox is indexed with [0], [1], [2], [3] (4 elements: x1, y1, x2, y2)
# We need to create a minimal face_model that has a get() method

class MockFaceModel(nn.Module):
    def __init__(self):
        super().__init__()
    
    def get(self, image_bgr):
        # Return a list of face info dicts with bboxes
        # Each bbox is [x1, y1, x2, y2]
        return [
            {
                'bbox': [10, 20, 50, 80],  # width=40, height=60, area=2400
                'keypoints': np.array([[15, 25], [45, 30]])
            },
            {
                'bbox': [100, 100, 200, 250],  # width=100, height=150, area=15000
                'keypoints': np.array([[120, 120], [180, 200]])
            }
        ]

# Create instances
face_model = MockFaceModel()

# Create a mock BGR image (numpy array with shape H x W x 3)
image_bgr = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)

ARGS = {
    'face_model': face_model,
    'image_bgr': image_bgr
}
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_resize_crop_region_for_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feizc/ingredients/models/pipeline_ingredients.py
code served (permissive licence) · get_code("734fd43f6aaef115")
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 2, dtype family int; 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 numpy as np

# The function takes:
# - src: a tuple of (height, width) dimensions
# - tgt_width: target width (int)
# - tgt_height: target height (int)

ARGS = {
    "src": (480, 640),           # source dimensions as (height, width)
    "tgt_width": 224,            # target width
    "tgt_height": 224            # target height
}
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, ndim 2, dtype family int — 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
load_image Ran
ran on a synthesized input
feizc/ingredients/metric/face_sim_fid.py
code served (permissive licence) · get_code("18703ab999a62c3e")
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 (1, 3, 299, 299) 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 PIL import Image
import numpy as np

# Create a small PIL Image object
# The function expects a PIL Image with a convert method and the ability to be resized
img_array = np.random.randint(0, 256, (64, 64, 3), dtype=np.uint8)
pil_image = Image.fromarray(img_array, mode='RGB')

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, 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 (1, 3, 299, 299) — shape (1, 3, 299, 299) 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
reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feizc/ingredients/models/local_facial_extractor.py
pointer only (licence: Apache-2.0); 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: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Minyeol/MIDAS, 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.

retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/models/pipeline_cogvideox.py
code served (permissive licence) · get_code("22b1f260da28f6a5")
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 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 inspect
from typing import List, Optional, Union

torch.manual_seed(0)

class MockScheduler:
    """Mock scheduler that implements set_timesteps and has timesteps attribute."""
    
    def __init__(self, supports_timesteps=True, supports_sigmas=False):
        self.supports_timesteps = supports_timesteps
        self.supports_sigmas = supports_sigmas
        self.timesteps = torch.tensor([999, 500, 250, 0], dtype=torch.long)
        self._device = None
    
    def set_timesteps(self, num_inference_steps: Optional[int] = None, 
                      device: Optional[Union[str, torch.device]] = None,
                      timesteps: Optional[List[int]] = None,
                      sigmas: Optional[List[float]] = None,
                      **kwargs):
        """Mock set_timesteps method."""
        self._device = device
        
        if timesteps is not None:
            self.timesteps = torch.tensor(timesteps, dtype=torch.long)
        elif sigmas is not None:
            # Create timesteps from sigmas
            self.timesteps = torch.tensor([int(s * 1000) for s in sigmas], dtype=torch.long)
        elif num_inference_steps is not None:
            # Create default timesteps
            self.timesteps = torch.linspace(999, 0, num_inference_steps, dtype=torch.long)
        
        if device is not None:
            self.timesteps = self.timesteps.to(device)

# Create a basic scheduler instance
scheduler = MockScheduler(supports_timesteps=True, supports_sigmas=False)

ARGS = {
    "scheduler": scheduler,
    "num_inference_steps": 4,
    "device": "cpu",
    "timesteps": None,
    "sigmas": None,
}
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 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
sample_video_frames Ran
ran on a synthesized input
feizc/ingredients/metric/face_sim_fid.py
code served (permissive licence) · get_code("8d3e6b254561c7ec")
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 4, dtype family int; 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary video file for testing
temp_dir = tempfile.gettempdir()
video_path = os.path.join(temp_dir, "test_video.mp4")

# Create a simple test video using OpenCV
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
fps = 30
frame_size = (640, 480)
out = cv2.VideoWriter(video_path, fourcc, fps, frame_size)

# Write 100 frames of random data
for i in range(100):
    frame = np.random.randint(0, 255, (frame_size[1], frame_size[0], 3), dtype=np.uint8)
    out.write(frame)

out.release()

# Define arguments for the function
ARGS = {
    "video_path": video_path,
    "num_frames": 24
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, dtype family int — 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
tensor_to_pil Ran
ran; our contract draft was wrong, not the code
feizc/ingredients/models/utils.py
code served (permissive licence) · get_code("aabdf33f95d21edf")
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 Image. 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 PIL import Image

torch.manual_seed(0)

# Create a valid image tensor
# Shape: (C, H, W) where C=3 (RGB), H=4, W=5
# Values in range [0, 255] as uint8-compatible
src_img_tensor = torch.randint(0, 256, (3, 4, 5), dtype=torch.uint8).float()

ARGS = {
    "src_img_tensor": src_img_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 Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
IR_18 Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/metric/curricularface/model_irse.py
code served (permissive licence) · get_code("42efa8d0cbd120d8")
How it ran

no invocation recorded.

ResNet_50 Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/metric/curricularface/model_resnet.py
code served (permissive licence) · get_code("d6583b15d8a7722f")
How it ran

no invocation recorded.

compute_clip_score Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/metric/clip_score.py
code served (permissive licence) · get_code("7b654be5a00e575f")
How it ran

no invocation recorded.

encode_prompt Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/models/utils.py
code served (permissive licence) · get_code("9ca4e9fb5eb8034d")
How it ran

no invocation recorded.

get_model_config Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/models/eva_clip/factory.py
code served (permissive licence) · get_code("5c7cf820e99443ff")
How it ran

no invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/models/eva_clip/factory.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from winycg/clip-kd, is pointer only (licence: NONE) · get_code("9b7c99fcbb58f26f")
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 winycg/clip-kd, 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. No invocation recorded.

load_state_dict Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/models/eva_clip/factory.py
code served (permissive licence) · get_code("ab854bdad372c33e")
How it ran

no invocation recorded.

process_image Not yet run
unverified (harvested, no recorded run)
feizc/ingredients/models/pipeline_ingredients.py
code served (permissive licence) · get_code("c17ad34b7b0cba0e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 17 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 1 the same month, 12 later) and 5 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
FeedForward 47 other papers
35 dated earlier, 10 later, 2 same year, order not determinable · 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
retrieve_timesteps 46 other papers
14 dated earlier, 2 the same month, 27 later, 1 same year, order not determinable, 2 undated
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2402.10491 (2024-02)
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
2405.18991 (2024-05)
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
and 43 more not named here
reshape_tensor 30 other papers
22 dated earlier, 6 later, 2 same year, order not determinable
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
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
and 27 more not named here
get_block 27 other papers
25 dated earlier, 2 later
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
1907.10830 (2019-07)
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
and 24 more not named here
get_model_config 22 other papers
20 dated earlier, 2 later
2211.07636 (2022-11)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
2303.14814 (2023-03)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
and 19 more not named here
conv3x3 9 other papers
8 dated earlier, 1 later
2001.06838 (2020-01)
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
2004.00288 (2020-04)
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
2107.08621 (2021-07)
Face.evoLVe: A High-Performance Face Recognition Library
and 6 more not named here
conv1x1 8 other papers
8 dated earlier
2001.06838 (2020-01)
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
2004.00288 (2020-04)
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
2008.04115 (2020-08)
T-GD: Transferable GAN-generated Images Detection Framework
and 5 more not named here
get_resize_crop_region_for_grid 8 other papers
3 dated earlier, 5 later
2405.18991 (2024-05)
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
2407.21705 (2024-07)
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
2410.07659 (2024-10)
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
and 5 more not named here
ResNet_50 4 other papers
4 dated earlier
2004.00288 (2020-04)
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
2107.08621 (2021-07)
Face.evoLVe: A High-Performance Face Recognition Library
2210.10090 (2022-10)
How to Boost Face Recognition with StyleGAN?
and 1 more not named here
encode_prompt 4 other papers
1 dated earlier, 3 later
2412.00596 (2024-12)
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
2502.13995 (2025-02)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation
2503.20287 (2025-03)
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction
and 1 more not named here
compute_prompt_embeddings 3 other papers
1 dated earlier, 2 later
2412.00596 (2024-12)
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
2502.13995 (2025-02)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation
2503.20287 (2025-03)
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction
draw_kps 3 other papers
3 later
2502.13995 (2025-02)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation
2503.16418 (2025-03)
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
2505.20292 (2025-05)
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
get_blocks 3 other papers
3 dated earlier
2204.00964 (2022-04)
AdaFace: Quality Adaptive Margin for Face Recognition
2405.15020 (2024-05)
AdjointDEIS: Efficient Gradients for Diffusion Models
2408.05939 (2024-08)
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
IR_18 1 other paper
1 dated earlier
2408.05939 (2024-08)
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
get_tokenizer 1 other paper
1 dated earlier
2307.12732 (2023-07)
CLIP-KD: An Empirical Study of CLIP Model Distillation
process_image 1 other paper
1 later
2502.13995 (2025-02)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation
tensor_to_pil 1 other paper
1 later
2502.13995 (2025-02)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation

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

This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as Ingredients. Generally, our method consists of three primary modules: (i) a facial extractor that captures versatile and precise facial features for each human ID from both global and local perspectives; (ii) a multi-scale projector that maps face embeddings into the contextual space of image query in video diffusion transformers; (iii) an ID router that dynamically combines and allocates multiple ID embedding to the corresponding space-time regions. Leveraging a meticulously curated text-video dataset and a multi-stage training protocol, Ingredients demonstrates superior performance in turning custom photos into dynamic and personalized video content. Qualitative evaluations highlight the advantages of proposed method, positioning it as a significant advancement toward more effective generative video control tools in Transformer-based architecture, compared to existing methods. The data, code, and model weights are publicly available at: https://github.com/feizc/Ingredients.

For agents

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

get_harvested_code_for_paper("2501.01790")
get_code_for_paper("2501.01790")
have("2501.01790")

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

curl https://syntology.ai/api/ran/2501.01790.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.01790.svg)](https://syntology.ai/paper/2501.01790)

Connect an agent — have() is free.