Papers › I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models

I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models

27 Dec 2023arXiv:2312.16693archive 2025-07-28

Xun Guo, Mingwu Zheng, Liang Hou, Yuan Gao, Yufan Deng, Pengfei Wan, Di Zhang, Yufan Liu, Weiming Hu, ZhengJun Zha, Haibin Huang, Chongyang Ma

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 29 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 13 ran (3 with no instrument failure; 10 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

KwaiVGI/I2V-Adapter officialmentioned on GitHubpytorchSyntology: 17 samples, 13 ran (10 instrument-failed) · 4 unverified report
bytedance/x-dyna mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 7 ran (2 instrument-failed) · 5 unverified 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

29 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
8ran · our draft was wrong
4ran; the contract check could not run
6ran
9unverified

Licence: 18 of the 29 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

KwaiVGI/I2V-Adapter official repository 17 samples, 13 ran (10 instrument-failed) · 4 unverified
FeedForward in 198 papers src/models/ip_adapter.py ran · our draft was wrong no licence file found · pointer only · 5105747c2711b1cb · report fixture: signature dim:int/0/int, mult:int/0/int · returned Sequential · level recorded 2026-09-22
freq_mix_3d src/utils/freeinit_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · e285f4a541803f96 · report fixture: signature x:Tensor/4/float, noise:Tensor/4/float, LPF:Tensor/4/float · returned Tensor · level recorded 2026-09-22
gaussian_low_pass_filter src/utils/freeinit_utils.py ran · our draft was wrong no licence file found · pointer only · 5753a1ae1b2b2a7a · report fixture: signature shape:tuple/1/int, d_s:float/0/float, d_t:float/0/float · returned Tensor · level recorded 2026-09-22
get_freq_filter src/utils/freeinit_utils.py ran no licence file found · pointer only · 924dfd50e7486609 · report fixture: signature shape:tuple/1/int, device:str/0/str, params:FilterParams/0/? · returned Tensor · level recorded 2026-09-24
imread_resize src/utils/util.py ran no licence file found · pointer only · e00393f9090e49e9 · report fixture: signature path:str/0/str, h_max:int/0/int, w_max:int/0/int · returned ndarray · level recorded 2026-09-24
masked_mean in 74 papers
census: 8 implementations from 11 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
src/models/ip_adapter.py ran · our draft was wrong no licence file found · pointer only · 230588e8f1237737 · report fixture: signature t:Tensor/3/float, dim:int/0/int, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-25
match_histogram src/utils/util.py ran · honoured contract no licence file found · pointer only · d8bea9099f8a52b0 · report fixture: signature source:ndarray/2/int, template:ndarray/2/int · returned ndarray · level recorded 2026-09-24
renew_resnet_paths in 15 papers src/utils/convert_from_ckpt.py ran · our draft was wrong no licence file found · pointer only · dfb052a0af48540f · report fixture: signature old_list:list/1/str, n_shave_prefix_segments:int/0/int · returned list · level recorded 2026-09-25
renew_vae_resnet_paths in 12 papers src/utils/convert_from_ckpt.py ran · our draft was wrong no licence file found · pointer only · c5ec9c13e456a046 · report fixture: signature old_list:list/1/str, n_shave_prefix_segments:int/0/int · returned list · level recorded 2026-09-26
reshape_tensor in 31 papers src/models/ip_adapter.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4cb2e2a2ca0bec9f · report fixture: signature x:Tensor/3/float, heads:int/0/int · returned Tensor · level recorded 2026-09-25
resize_image in 74 papers src/utils/util.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2e3e408dc6b5d79d · report fixture: signature input_image:ndarray/3/int, resolution:int/0/int · returned ndarray · level recorded 2026-09-24
shave_segments in 15 papers src/utils/convert_from_ckpt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cea0bc82e0c96896 · report fixture: signature path:str/0/str, n_shave_prefix_segments:int/0/int · returned str · level recorded 2026-09-25
zero_module in 184 papers src/models/motion_module.py ran · our draft was wrong no licence file found · pointer only · 4719c763c53be3fe · report fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-22
convert_lora in 8 papers src/utils/convert_lora_safetensor_to_diffusers.py unverified no licence file found · pointer only · 4e1c711f8f37a1e7 · report
convert_motion_lora_ckpt_to_diffusers src/utils/convert_lora_safetensor_to_diffusers.py unverified no licence file found · pointer only · ef399950f86ca4fc · report
get_down_block in 42 papers src/models/unet_blocks.py unverified no licence file found · pointer only · 8b6c18061cbaa5fd · report
get_up_block in 43 papers src/models/unet_blocks.py unverified no licence file found · pointer only · 07607267678d0f69 · report
bytedance/x-dyna community (archive-listed) 12 samples, 7 ran (2 instrument-failed) · 5 unverified
extract_local_feature_from_single_img inference_xdyna.py ran Apache-2.0 (permissive) · 82ba71457fd0972f · report fixture: signature img:ndarray/3/int, fa:MockFaceAligner/0/?, nms_processor:MockNMSProcessor/0/?, last_bbox:list/1/int, last_center:list/1/ndarray, remove_local:bool/0/bool, real_tocrop:Tensor/3/float · returned tuple · level recorded 2026-09-24
find_best_frame_byheadpose_fa inference_xdyna.py ran Apache-2.0 (permissive) · bf7f7ded00990ac3 · report fixture: signature source_image:ndarray/3/float, driving_video:list/1/ndarray, fa:Landmarks/0/? · returned int · level recorded 2026-09-24
get_2d_sincos_pos_embed in 170 papers animatediff/models/embeddings.py ran · honoured contract Apache-2.0 (permissive) · 45f1cb4de58b3f3d · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool, extra_tokens:int/0/int · returned ndarray · level recorded 2026-09-24
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
animatediff/models/embeddings.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 38f69a3d1e46016d · report fixture: signature timesteps:Tensor/1/float, embedding_dim:int/0/int, flip_sin_to_cos:bool/0/bool, downscale_freq_shift:float/0/float, scale:float/0/float, max_period:int/0/int · returned Tensor · level recorded 2026-09-26
is_valid_image animatediff/models/image_processor.py ran Apache-2.0 (permissive) · c9903af7cf272bc4 · report fixture: signature image:Image/0/? · returned bool · level recorded 2026-09-25
is_valid_image_imagelist animatediff/models/image_processor.py ran fingerprinted Apache-2.0 (permissive) · 53ccc214b8346dff · report fixture: signature images:Tensor/4/float · returned bool · level recorded 2026-09-25
zero_module in 184 papers animatediff/models/controlnet.py ran · our draft was wrong Apache-2.0 (permissive) · da94debb8019ad46 · report fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-25
adjust_driving_video_to_src_image inference_xdyna.py unverified Apache-2.0 (permissive) · c8b7b26f11f30946 · report
get_2d_sincos_pos_embed_from_grid in 140 papers animatediff/models/embeddings.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 59fa7b38de05f443 · report
get_down_block in 42 papers animatediff/models/unet_blocks.py unverified Apache-2.0 (permissive) · 5f11ee52e92689bd · report
get_motion_module in 12 papers animatediff/models/motion_module.py unverified Apache-2.0 (permissive) · cd5f3777a951d27f · report
get_up_block in 43 papers animatediff/models/unet_blocks.py unverified Apache-2.0 (permissive) · c5952d08a7df1728 · report

Tasks

Video Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterDiffusionFocus

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