SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.18264 · 2023

Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 5 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/2305.18264.json · badge: /api/ran/2305.18264.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
g-u-n/gen-l-video canonical (classifier label)
classifier basis: census
3 ran · 5 no recorded run
FunctionStatusWhere it lives
check_imgorstr Ran
ran on a synthesized input
g-u-n/gen-l-video/process_data.py
code served (permissive licence) · get_code("6799486af9833123")
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 function. 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
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.gettempdir()
temp_image_path = os.path.join(temp_dir, "test_image.png")
test_array = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
test_image = Image.fromarray(test_array)
test_image.save(temp_image_path)

# Define a simple function to wrap with the decorator
def dummy_fn(self, img_or_path):
    """Dummy function that expects an image array as second argument"""
    if isinstance(img_or_path, np.ndarray):
        return img_or_path.shape
    return None

# The check_imgorstr decorator takes a function as input
# It returns a decorator function that wraps the original function

ARGS = {
    "fn": dummy_fn
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_lora Ran
ran on a synthesized input
g-u-n/gen-l-video/glv/lora_util.py
code served (permissive licence) · get_code("40e0e530ca65996d")
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 LoraInjectedLinear. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal nn.Linear module to pass to get_lora
in_features = 4
out_features = 3
module = nn.Linear(in_features, out_features, bias=True)

# Verify the module has the required attributes
assert hasattr(module, 'weight')
assert hasattr(module, 'bias')
assert hasattr(module, 'in_features')
assert hasattr(module, 'out_features')

ARGS = {
    'module': module,
    'r': 2,
    'dropout_p': 0.1,
    'scale': 1.0,
    'stride': 4,
    'num_loras': 50
}
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 LoraInjectedLinear — a LoraInjectedLinear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LoraInjectedLinear 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
show_anns Ran
ran on a synthesized input
g-u-n/gen-l-video/tuning-free-inpaint.py
code served (permissive licence) · get_code("2b1e9a978286a083")
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 4, dtype family float; 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 numpy as np

# Create sample annotations with segmentation masks and areas
# The function expects a list of dicts, each with 'segmentation' (ndarray) and 'area' (numeric) keys

# Create two sample segmentation masks of different sizes to test the function
mask1 = np.random.rand(4, 3) > 0.5  # 4x3 binary mask
mask2 = np.random.rand(4, 3) > 0.5  # 4x3 binary mask

ann1 = {
    'segmentation': mask1.astype(np.uint8),
    'area': 5
}

ann2 = {
    'segmentation': mask2.astype(np.uint8),
    'area': 8
}

anns = [ann1, ann2]

ARGS = {
    'anns': anns
}
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 tuple, ndim 4, dtype family float — 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
avg_pool_nd Not yet run
unverified (harvested, no recorded run)
g-u-n/gen-l-video/glv/models/unet.py
code served (permissive licence) · get_code("ecd0fc28815b65ae")
How it ran

no invocation recorded.

conv_nd Not yet run
unverified (harvested, no recorded run)
g-u-n/gen-l-video/glv/models/unet.py
code served (permissive licence) · get_code("fe4eb545bbb728e0")
How it ran

no invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
g-u-n/gen-l-video/glv/models/unet_blocks.py
code served (permissive licence) · get_code("6663aa5ed50afee8")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
g-u-n/gen-l-video/glv/models/unet_blocks.py
code served (permissive licence) · get_code("1f6734cce50b9e27")
How it ran

no invocation recorded.

inject_trainable_lora Not yet run
unverified (harvested, no recorded run)
g-u-n/gen-l-video/glv/lora_util.py
code served (permissive licence) · get_code("9edad189fe9ade2c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 4 the same month, 4 later) and 4 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
conv_nd 121 other papers
40 dated earlier, 3 the same month, 77 later, 1 same year, order not determinable · 32 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 118 more not named here
avg_pool_nd 113 other papers
40 dated earlier, 4 the same month, 68 later, 1 same year, order not determinable · 31 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 110 more not named here
get_down_block 10 other papers
3 dated earlier, 1 the same month, 6 later
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
and 7 more not named here
get_up_block 10 other papers
3 dated earlier, 1 the same month, 6 later
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2212.11565 (2022-12)
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
2304.01186 (2023-04)
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
and 7 more not named here

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

Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically less than 24 frames) and are limited to a single text condition. These constraints significantly limit their applications given that real-world videos usually consist of multiple segments, each bearing different semantic information. To address this challenge, we introduce a novel paradigm dubbed as Gen-L-Video, capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising hundreds of frames with diverse semantic segments without introducing additional training, all while preserving content consistency. We have implemented three mainstream text-driven video generation and editing methodologies and extended them to accommodate longer videos imbued with a variety of semantic segments with our proposed paradigm. Our experimental outcomes reveal that our approach significantly broadens the generative and editing capabilities of video diffusion models, offering new possibilities for future research and applications. The code is available at https://github.com/G-U-N/Gen-L-Video.

For agents

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

get_harvested_code_for_paper("2305.18264")
get_code_for_paper("2305.18264")
have("2305.18264")

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

curl https://syntology.ai/api/ran/2305.18264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.18264.svg)](https://syntology.ai/paper/2305.18264)

Connect an agent — have() is free.