SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.01256 · 2024

VideoStudio: Generating Consistent-Content and Multi-Scene Videos

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 0 failures of our instrument; 0 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/2401.01256.json · badge: /api/ran/2401.01256.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
fuchenustc/videostudio canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
load_action_prototype Ran
ran, honoured the contract we drafted
fuchenustc/videostudio/videostudio_vid/infer_videostudio_vid.py
code served (permissive licence) · get_code("ea0a680ac049a78c")
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 ndarray, ndim 2, dtype family float, shape (5, 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 numpy as np
import tempfile
import os

# Create a temporary numpy file to serve as the action prototype file
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "action_prototypes.npy")

# Create sample action prototype data
action_prototypes_data = np.random.randn(5, 4).astype(np.float32)
np.save(temp_file, action_prototypes_data)

ARGS = {
    "file_path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (5, 4) — shape (5, 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
load_first_frame Ran
ran, honoured the contract we drafted
fuchenustc/videostudio/videostudio_vid/infer_videostudio_vid.py
code served (permissive licence) · get_code("96902150efb7a36d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 5, dtype family float, shape (1, 3, 1, 32, 32) 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 torchvision.transforms as transforms
from PIL import Image
import io

torch.manual_seed(0)

# Create a small dummy image in memory
img_array = torch.randint(0, 256, (32, 32, 3), dtype=torch.uint8).numpy()
img_pil = Image.fromarray(img_array, mode='RGB')
img_bytes = io.BytesIO()
img_pil.save(img_bytes, format='PNG')
img_bytes.seek(0)

# Create a temporary file-like object that can be opened
class FakeImagePath:
    def __init__(self, img_bytes):
        self.img_bytes = img_bytes
    
    def __str__(self):
        return "fake_image.png"

# Since we can't do real file I/O, we'll monkey-patch Image.open
original_open = Image.open
def mock_open(path, *args, **kwargs):
    img_bytes = io.BytesIO()
    img_array = torch.randint(0, 256, (32, 32, 3), dtype=torch.uint8).numpy()
    img_pil = Image.fromarray(img_array, mode='RGB')
    img_pil.save(img_bytes, format='PNG')
    img_bytes.seek(0)
    return original_open(img_bytes)

Image.open = mock_open

# Define image transform
image_transform = transforms.Compose([
    transforms.ToTensor(),
])

ARGS = {
    'image_path': 'dummy_image.png',
    'image_transform': image_transform,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, 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 5, dtype family float, shape (1, 3, 1, 32, 32) — shape (1, 3, 1, 32, 32) 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

The recent innovations and breakthroughs in diffusion models have significantly expanded the possibilities of generating high-quality videos for the given prompts. Most existing works tackle the single-scene scenario with only one video event occurring in a single background. Extending to generate multi-scene videos nevertheless is not trivial and necessitates to nicely manage the logic in between while preserving the consistent visual appearance of key content across video scenes. In this paper, we propose a novel framework, namely VideoStudio, for consistent-content and multi-scene video generation. Technically, VideoStudio leverages Large Language Models (LLM) to convert the input prompt into comprehensive multi-scene script that benefits from the logical knowledge learnt by LLM. The script for each scene includes a prompt describing the event, the foreground/background entities, as well as camera movement. VideoStudio identifies the common entities throughout the script and asks LLM to detail each entity. The resultant entity description is then fed into a text-to-image model to generate a reference image for each entity. Finally, VideoStudio outputs a multi-scene video by generating each scene video via a diffusion process that takes the reference images, the descriptive prompt of the event and camera movement into account. The diffusion model incorporates the reference images as the condition and alignment to strengthen the content consistency of multi-scene videos. Extensive experiments demonstrate that VideoStudio outperforms the SOTA video generation models in terms of visual quality, content consistency, and user preference. Source code is available at \url{https://github.com/FuchenUSTC/VideoStudio}.

For agents

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

get_harvested_code_for_paper("2401.01256")
get_code_for_paper("2401.01256")
have("2401.01256")

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

curl https://syntology.ai/api/ran/2401.01256.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.01256.svg)](https://syntology.ai/paper/2401.01256)

Connect an agent — have() is free.