Papers › ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation

6 Feb 2024arXiv:2402.04324archive 2025-07-28

Weiming Ren, Huan Yang, Ge Zhang, Cong Wei, Xinrun Du, Wenhao Huang, Wenhu Chen

Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first frame to maintain spatial and motion consistency, (2) noise initialization from the low-frequency band of the first frame to enhance layout consistency. These two approaches enable ConsistI2V to generate highly consistent videos. We also extend the proposed approaches to show their potential to improve consistency in auto-regressive long video generation and camera motion control. To verify the effectiveness of our method, we propose I2V-Bench, a comprehensive evaluation benchmark for I2V generation. Our automatic and human evaluation results demonstrate the superiority of ConsistI2V over existing methods.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.04324")

Code

Syntology Ran 11 of 12 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

TIGER-AI-Lab/ConsistI2V officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 11 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
5ran
1unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from TIGER-AI-Lab/ConsistI2V. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

broadcat TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.py official repository ran MIT (permissive) · f07bf3d46feead4c · report
default TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.py official repository ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
exists TIGER-AI-Lab/ConsistI2V/consisti2v/models/rotary_embedding.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
freq_mix_3d TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · e285f4a541803f96 · report
gaussian_low_pass_filter TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py official repository ran · our draft was wrong MIT (permissive) · 5753a1ae1b2b2a7a · report
get_freq_filter TIGER-AI-Lab/ConsistI2V/consisti2v/utils/frameinit_utils.py official repository ran · fixture could not drive it MIT (permissive) · e6e9076eaee4d40e · report
get_noise_pred_single TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py official repository ran MIT (permissive) · 5c98cd544c2fe28d · report
next_step TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py official repository ran MIT (permissive) · fb032d6fa7e6196d · report
pan_left TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_conditional_animation.py official repository ran MIT (permissive) · 6a8efc5f6a39c807 · report
pan_right TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_conditional_animation.py official repository ran MIT (permissive) · b2e8efa1d185957b · report
rescale_noise_cfg TIGER-AI-Lab/ConsistI2V/consisti2v/pipelines/pipeline_autoregress_animation.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · bea2d776a332f2b0 · report
init_prompt TIGER-AI-Lab/ConsistI2V/consisti2v/utils/util.py official repository unverified MIT (permissive) · a0a4d94af120c56f · report

Tasks

Image to Video GenerationVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections