SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09535 · ICCV · 2023

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

Chenyang Lei, Qifeng Chen, Yong Zhang, Hkust, Ying Shan, Xintao Wang, Chenyang Qi, Xiaodong Cun, In Denoising

arXiv · PDF · Open in the Atlas

Code that ran

8 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, 0 violated it and 1 has no contract verdict; 6 failures of our instrument; 4 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/2303.09535.json · badge: /api/ran/2303.09535.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
chenyangqiqi/fatezero canonical (classifier label)
classifier basis not recorded on the link
8 ran · 4 no recorded run
FunctionStatusWhere it lives
basic_clean Ran
ran; our contract draft was wrong, not the code
chenyangqiqi/fatezero/CLIP/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
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 ltpwy/MSCI, 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.

collate_fn Ran
ran; our contract draft was wrong, not the code
chenyangqiqi/fatezero/train_tune_a_video.py
pointer only (licence: MIT); the stored copy get_code serves, from YangLing0818/ContextDiff, is pointer only (licence: NONE) · get_code("aad535655c5f6b0f")
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 YangLing0818/ContextDiff, 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.

crop_read_image_path Ran
ran, honoured the contract we drafted
chenyangqiqi/fatezero/CLIP/frame_acc_tem_con.py
code served (permissive licence) · get_code("92f6ba552dffd628")
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 tempfile
import os
from PIL import Image
import numpy as np

# Create a temporary directory and image file
temp_dir = tempfile.mkdtemp()

# Create a test image with height > width (portrait orientation)
# Image size: width=100, height=150
img_array = np.random.randint(0, 256, (150, 100, 3), dtype=np.uint8)
test_image = Image.fromarray(img_array)
image_path = os.path.join(temp_dir, "test_image.png")
test_image.save(image_path)

ARGS = {
    "image_path": image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
downsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenyangqiqi/fatezero/video_diffusion/models/resnet.py
code served (permissive licence) · get_code("f46bcb6099334fa6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 4, 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

torch.manual_seed(0)

# Create a small batch of 2D images with shape [N, C, H, W]
# N=2 (batch size), C=3 (channels), H=8 (height), W=8 (width)
hidden_states = torch.randn(2, 3, 8, 8)

# Create a kernel - can be 1D or 2D
# Using a simple 1D kernel that will be converted to 2D via outer product
kernel = [1, 1]

# Downsampling factor
factor = 2

# Gain scaling factor
gain = 1.0

ARGS = {
    "hidden_states": hidden_states,
    "kernel": kernel,
    "factor": factor,
    "gain": gain,
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
get_pairs Ran
ran; our contract draft was wrong, not the code
chenyangqiqi/fatezero/CLIP/clip/simple_tokenizer.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
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 set. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function get_pairs takes a word parameter
# A word is represented as a tuple of symbols (variable-length strings)
# The function iterates through the word and creates pairs of consecutive symbols

word = ("hello", "world", "test")

ARGS = {
    "word": word
}
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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
upfirdn2d_native Ran
ran on a synthesized input
chenyangqiqi/fatezero/video_diffusion/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from ian-jihoonpark/X-Diffusion, is pointer only (licence: NONE) · get_code("d3ea46d2b896a593")
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 ian-jihoonpark/X-Diffusion, 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.

upsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenyangqiqi/fatezero/video_diffusion/models/resnet.py
code served (permissive licence) · get_code("31e7ed79c46ee9a9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 6, 10) 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 a small input tensor [N, C, H, W]
hidden_states = torch.randn(2, 4, 3, 5)

# Create a simple kernel (1D that will be converted to 2D)
kernel = [1.0, 1.0]

# Upsampling factor
factor = 2

# Gain scaling factor
gain = 1.0

ARGS = {
    "hidden_states": hidden_states,
    "kernel": kernel,
    "factor": factor,
    "gain": gain,
}
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 4, dtype family float, shape (2, 4, 6, 10) — shape (2, 4, 6, 10) 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
whitespace_clean Ran
ran; our contract draft was wrong, not the code
chenyangqiqi/fatezero/CLIP/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
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 ltpwy/MSCI, 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.

build_model Not yet run
unverified (harvested, no recorded run)
chenyangqiqi/fatezero/CLIP/clip/model.py
code served (permissive licence) · get_code("39e6b23b55f376ea")
How it ran

no invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
chenyangqiqi/fatezero/video_diffusion/models/unet_3d_blocks.py
code served (permissive licence) · get_code("032954630a69a9df")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
chenyangqiqi/fatezero/video_diffusion/models/unet_3d_blocks.py
code served (permissive licence) · get_code("75eee0ffe8b4fafe")
How it ran

no invocation recorded.

load Not yet run
unverified (harvested, no recorded run)
chenyangqiqi/fatezero/CLIP/clip/clip.py
pointer only (licence: MIT); the stored copy get_code serves, from mrflogs/ICLR24, is pointer only (licence: NONE) · get_code("f6f30e41636ae569")
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 mrflogs/ICLR24, 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.

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, 10 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 10 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_pairs 258 other papers
46 dated earlier, 4 the same month, 200 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
31 dated earlier, 4 the same month, 190 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
31 dated earlier, 4 the same month, 177 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
build_model 53 other papers
5 dated earlier, 1 the same month, 47 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2211.09552 (2022-11)
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
and 50 more not named here
load 23 other papers
4 dated earlier, 1 the same month, 17 later, 1 undated
2208.05318 (2022-08)
Generative Action Description Prompts for Skeleton-based Action Recognition
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2212.04501 (2022-12)
Learning Video Representations from Large Language Models
and 20 more not named here
downsample_2d 7 other papers
7 later
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
2310.01107 (2023-10)
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
and 4 more not named here
upsample_2d 7 other papers
7 later
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
2310.01107 (2023-10)
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
and 4 more not named here
upfirdn2d_native 2 other papers
2 later
2310.01107 (2023-10)
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
2402.10404 (2024-02)
Explaining generative diffusion models via visual analysis for interpretable decision-making process
collate_fn 1 other paper
1 later
2402.16627 (2024-02)
Contextualized Diffusion Models for Text-Guided Image and Video Generation
crop_read_image_path 1 other paper
1 later
2409.09668 (2024-09)
EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing 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

Zero-shot object shape editing with pre-trained video diffusion model [52]: silver jeep -→ Porsche car. Zero-shot video style editing with pre-trained image diffusion model [42]: watercolor painting. Figure 1. Zero-shot text-driven video editing. We present a zero-shot approach for shape-aware local object editing and video style editing from pre-trained diffusion models [42,52] without any optimization for each target prompt.

For agents

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

get_harvested_code_for_paper("2303.09535")
get_code_for_paper("2303.09535")
have("2303.09535")

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

curl https://syntology.ai/api/ran/2303.09535.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09535.svg)](https://syntology.ai/paper/2303.09535)

Connect an agent — have() is free.