SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02813 · 2023

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 0 have no contract verdict; 2 failures of our instrument; 3 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/2312.02813.json · badge: /api/ran/2312.02813.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
mcg-nju/bivdiff canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
mcg-nju/bivdiff/models/scheduling_ddim.py
code served (permissive licence) · get_code("4b1e4330d47f40f3")
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 1, dtype family float, shape (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
import math

torch.manual_seed(0)

ARGS = {
    "num_diffusion_timesteps": 10,
    "max_beta": 0.999,
}
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 1, dtype family float, shape (10,) — shape (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
rescale_noise_cfg Ran
ran; our contract draft was wrong, not the code
mcg-nju/bivdiff/models/Prompt2Prompt/pipeline_prompt2prompt.py
code served (permissive licence) · get_code("bea2d776a332f2b0")
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 4, dtype family float, shape (2, 4, 3, 3) 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 small tensors with distinct dimensions
# noise_cfg: shape (batch=2, channels=4, height=3, width=3)
noise_cfg = torch.randn(2, 4, 3, 3)

# noise_pred_text: shape (batch=2, channels=4, height=3, width=3)
noise_pred_text = torch.randn(2, 4, 3, 3)

# guidance_rescale: float between 0 and 1
guidance_rescale = 0.7

ARGS = {
    "noise_cfg": noise_cfg,
    "noise_pred_text": noise_pred_text,
    "guidance_rescale": guidance_rescale,
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 4, 3, 3) 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
update_alpha_time_word Ran
ran; our contract draft was wrong, not the code
mcg-nju/bivdiff/models/Prompt2Prompt/pipeline_prompt2prompt.py
code served (permissive licence) · get_code("f55cc06c1f75e2b8")
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 (10, 5, 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 torch

torch.manual_seed(0)

# alpha is a 3D tensor with shape (time_steps, prompt_count, word_count)
# Based on the function usage:
# - alpha.shape[0] is the time dimension
# - alpha.shape[2] is the word dimension
# - prompt_ind indexes into alpha.shape[1]
alpha = torch.randn(10, 5, 8)

# bounds can be either a float or tuple of two floats
bounds = (0.2, 0.8)

# prompt_ind is an integer index into the second dimension
prompt_ind = 2

# word_inds is optional - can be None or a tensor of word indices
word_inds = None

ARGS = {
    "alpha": alpha,
    "bounds": bounds,
    "prompt_ind": prompt_ind,
    "word_inds": word_inds
}
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 3, dtype family float, shape (10, 5, 8) — shape (10, 5, 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
create_controller Not yet run
unverified (harvested, no recorded run)
mcg-nju/bivdiff/models/Prompt2Prompt/pipeline_prompt2prompt.py
code served (permissive licence) · get_code("3a3a0a7b84790627")
How it ran

no invocation recorded.

infer_prompt2prompt Not yet run
unverified (harvested, no recorded run)
mcg-nju/bivdiff/models/Prompt2Prompt/infer.py
code served (permissive licence) · get_code("4f3220902109eef8")
How it ran

no invocation recorded.

init_prompt Not yet run
unverified (harvested, no recorded run)
mcg-nju/bivdiff/models/util.py
code served (permissive licence) · get_code("a0a4d94af120c56f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 4 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
rescale_noise_cfg 62 other papers
7 dated earlier, 3 the same month, 52 later
2206.02779 (2022-06)
Blended Latent Diffusion
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2309.06380 (2023-09)
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
and 59 more not named here
init_prompt 14 other papers
11 dated earlier, 1 the same month, 2 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 11 more not named here
betas_for_alpha_bar 3 other papers
2 dated earlier, 1 later
2306.04848 (2023-06)
Interpreting and Improving Diffusion Models from an Optimization Perspective
2308.13712 (2023-08)
Residual Denoising Diffusion Models
2403.11157 (2024-03)
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
update_alpha_time_word 2 other papers
2 later
2407.05282 (2024-07)
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
2407.10738 (2024-07)
AccDiffusion: An Accurate Method for Higher-Resolution Image 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

Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image editing, while downstream video synthesis tasks are less explored for several reasons. First, it requires huge memory and computation overhead to train a video generation foundation model. Even with video foundation models, additional costly training is still required for downstream video synthesis tasks. Second, although some works extend image diffusion models into videos in a training-free manner, temporal consistency cannot be well preserved. Finally, these adaption methods are specifically designed for one task and fail to generalize to different tasks. To mitigate these issues, we propose a training-free general-purpose video synthesis framework, coined as {\bf BIVDiff}, via bridging specific image diffusion models and general text-to-video foundation diffusion models. Specifically, we first use a specific image diffusion model (e.g., ControlNet and Instruct Pix2Pix) for frame-wise video generation, then perform Mixed Inversion on the generated video, and finally input the inverted latents into the video diffusion models (e.g., VidRD and ZeroScope) for temporal smoothing. This decoupled framework enables flexible image model selection for different purposes with strong task generalization and high efficiency. To validate the effectiveness and general use of BIVDiff, we perform a wide range of video synthesis tasks, including controllable video generation, video editing, video inpainting, and outpainting.

For agents

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

get_harvested_code_for_paper("2312.02813")
get_code_for_paper("2312.02813")
have("2312.02813")

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

curl https://syntology.ai/api/ran/2312.02813.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02813.svg)](https://syntology.ai/paper/2312.02813)

Connect an agent — have() is free.