Papers › OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

26 May 2025arXiv:2505.20292archive 2025-07-28

Shenghai Yuan, Xianyi He, Yufan Deng, Yang Ye, Jinfa Huang, Bin Lin, Chongyang Ma, Jiebo Luo, Li Yuan

Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus, consisting of (i) OpenS2V-Eval, a fine-grained benchmark, and (ii) OpenS2V-5M, a million-scale dataset. In contrast to existing S2V benchmarks inherited from VBench that focus on global and coarse-grained assessment of generated videos, OpenS2V-Eval focuses on the model's ability to generate subject-consistent videos with natural subject appearance and identity fidelity. For these purposes, OpenS2V-Eval introduces 180 prompts from seven major categories of S2V, which incorporate both real and synthetic test data. Furthermore, to accurately align human preferences with S2V benchmarks, we propose three automatic metrics, NexusScore, NaturalScore and GmeScore, to separately quantify subject consistency, naturalness, and text relevance in generated videos. Building on this, we conduct a comprehensive evaluation of 16 representative S2V models, highlighting their strengths and weaknesses across different content. Moreover, we create the first open-source large-scale S2V generation dataset OpenS2V-5M, which consists of five million high-quality 720P subject-text-video triples. Specifically, we ensure subject-information diversity in our dataset by (1) segmenting subjects and building pairing information via cross-video associations and (2) prompting GPT-Image-1 on raw frames to synthesize multi-view representations. Through OpenS2V-Nexus, we deliver a robust infrastructure to accelerate future S2V generation research.

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 38 code samples harvested from 2 repositories linked to this paper: 35 ran (of which 0 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 38 samples from 2 repositories, 35 ran (31 with no instrument failure; 4 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

PKU-YuanGroup/ConsisID officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 20 samples, 19 ran (3 instrument-failed) · 1 unverified report
PKU-YuanGroup/OpenS2V-Nexus officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 18 samples, 16 ran (1 instrument-failed) · 2 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

38 samples harvested: 35 ran (of which 0 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 4 where Syntology's instrument failed) · 3 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.

1ran · our draft was wrong
3ran; the contract check could not run
31ran
3unverified

Licence: 2 of the 38 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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.

PKU-YuanGroup/ConsisID official repository 20 samples, 19 ran (3 instrument-failed) · 1 unverified
compute_clip_score eval/get_clipscore.py ran Apache-2.0 (permissive) · a76adcb6d1cb698c · report fixture: signature video_path:str/0/str, model:callable/0/?, processor:callable/0/?, prompt:str/0/str, device:str/0/str, num_frames:int/0/int · returned float · level recorded 2026-09-25
compute_iou in 68 papers data_preprocess/step3_get_refine_track.py ran Apache-2.0 (permissive) · 02fb438e848b5140 · report fixture: signature box1:dict/0/?, box2:dict/0/? · returned float · level recorded 2026-09-25
draw_kps in 7 papers models/pipeline_consisid.py ran Apache-2.0 (permissive) · 82cd6f8d42b34198 · report fixture: signature image_pil:Image/0/?, kps:list/1/tuple, color_list:list/1/tuple · returned Image · level recorded 2026-09-25
draw_kps in 7 papers models/dataloader.py ran Apache-2.0 (permissive) · 3a9e3b5be46cd837 · report fixture: signature image_pil:Image/0/?, kps:ndarray/2/float, color_list:list/1/tuple · returned Image · level recorded 2026-09-25
estimate_num_people data_preprocess/step3_get_refine_track.py ran Apache-2.0 (permissive) · 7dba7c420770388f · report fixture: signature data:dict/0/? · returned int · level recorded 2026-09-25
extract_start_end_frames data_preprocess/step0_split_transition.py ran Apache-2.0 (permissive) · 105544ba1a7e2e90 · report fixture: signature scene_list:list/1/tuple · returned list · level recorded 2026-09-25
extract_useful_frames data_preprocess/step2_split_bbox_pose.py ran Apache-2.0 (permissive) · 0a24c9067eabcc84 · report fixture: signature json_file:str/0/str, video_file_path:str/0/str, min_valid_frames:int/0/int, tolerance:int/0/int · returned list · level recorded 2026-09-25
filter_by_confidence data_preprocess/step3_get_refine_track.py ran Apache-2.0 (permissive) · d924f2a63ea92f78 · report fixture: signature objects:dict/0/?, key:str/0/str, threshold:float/0/float · returned list · level recorded 2026-09-25
get_frame_indices_adjusted_for_face models/dataloader.py ran fingerprinted Apache-2.0 (permissive) · 9079583c3a47cfb8 · report fixture: signature valid_frames:list/1/int, n_frames:int/0/int · returned list · level recorded 2026-09-25
get_resize_crop_region_for_grid in 9 papers models/pipeline_consisid.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted Apache-2.0 (permissive) · 734fd43f6aaef115 · report fixture: signature src:tuple/1/int, tgt_width:int/0/int, tgt_height:int/0/int · returned tuple · level recorded 2026-09-22
get_valid_segments models/dataloader.py ran Apache-2.0 (permissive) · b28b986e34458c53 · report fixture: signature valid_frame:dict/0/?, tolerance:int/0/int · returned list · level recorded 2026-09-25
img2tensor in 7 papers models/consisid_utils.py ran Apache-2.0 (permissive) · 490b7b3290557c78 · report fixture: signature imgs:ndarray/3/int, bgr2rgb:bool/0/bool, float32:bool/0/bool · returned Tensor · level recorded 2026-09-25
is_face_large_enough_v2 data_preprocess/step2_split_bbox_pose.py ran Apache-2.0 (permissive) · a3ce59e07cea71df · report fixture: signature face_boxes:list/1/dict, threshold:int/0/int · returned bool · level recorded 2026-09-25
is_valid_frame data_preprocess/step2_split_bbox_pose.py ran Apache-2.0 (permissive) · e242ea5a02b7f13d · report fixture: signature frame_data:list/1/dict · returned bool · level recorded 2026-09-25
make_inference in 5 papers util/rife_model.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 44d67662b32e0a93 · report fixture: signature model:callable/0/?, I0:Tensor/2/float, I1:Tensor/2/float, upscale_amount:int/0/int, n:int/0/int · returned list · level recorded 2026-09-25
pad_image in 27 papers util/rife_model.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 371391555c7fdb5b · report fixture: signature img:Tensor/4/float, scale:float/0/float · returned Tensor · level recorded 2026-09-25
resize_numpy_image_long models/consisid_utils.py ran fingerprinted Apache-2.0 (permissive) · 06ccb8f5750bed65 · report fixture: signature image:ndarray/3/int, resize_long_edge:int/0/int · returned ndarray · level recorded 2026-09-25
retrieve_timesteps in 70 papers models/pipeline_consisid.py ran · our draft was wrong Apache-2.0 (permissive) · 22b1f260da28f6a5 · report fixture: signature scheduler:MockScheduler/0/?, num_inference_steps:int/0/int, device:str/0/str, timesteps:NoneType/0/?, sigmas:NoneType/0/? · returned tuple · level recorded 2026-09-22
to_gray models/consisid_utils.py ran fingerprinted Apache-2.0 (permissive) · b3d03bc9df04cdef · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-25
get_clipscore eval/get_clipscore.py unverified Apache-2.0 (permissive) · 2d051fb9d3d082bc · report
PKU-YuanGroup/OpenS2V-Nexus official repository 18 samples, 16 ran (1 instrument-failed) · 2 unverified
batch_cosine_similarity data_process/step1_get_bbox.py ran Apache-2.0 (permissive) · 83512e65814b2096 · report fixture: signature embedding_image:ndarray/2/float, embedding_frames:ndarray/2/float, device:str/0/str · returned ndarray · level recorded 2026-09-25
collate_fn in 500 papers data_process/step3-1_get_caption.py ran Apache-2.0 (permissive) · ea468804bf7f0516 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
collate_fn in 500 papers data_process/step4-1_get_tag_local.py ran Apache-2.0 (permissive) · 68791d7cdd051179 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
extract_data_from_response data_process/step4-1_get_tag_api.py ran fingerprinted Apache-2.0 (permissive) · 4451a25f7c22f79a · report fixture: signature response:str/0/str · returned tuple · level recorded 2026-09-25
extract_frames in 21 papers eval/get_naturalscore.py ran Apache-2.0 (permissive) · 7e425139d10d0ffa · report fixture: signature video_path:str/0/str, num_frames:int/0/int · returned list · level recorded 2026-09-25
extract_useful_frames data_process/step2_get_pure_person_clip.py ran Apache-2.0 (permissive) · 83dec4a87d876ee4 · report fixture: signature bbox_infos:dict/0/?, min_valid_frames:int/0/int, tolerance:int/0/int · returned list · level recorded 2026-09-25
filter_keywords data_process/step4-1_get_tag_api.py ran Apache-2.0 (permissive) · 3aa9a7211091e0a4 · report fixture: signature items:list/1/str, keywords:list/1/str · returned list · level recorded 2026-09-25
image_to_base64 in 17 papers eval/get_naturalscore.py ran fingerprinted Apache-2.0 (permissive) · 0839fae5f1a98534 · report fixture: signature image:ndarray/3/int · returned str · level recorded 2026-09-25
mask_to_polygon data_process/demo_dataloader.py ran fingerprinted Apache-2.0 (permissive) · 55841bf2feba5902 · report fixture: signature mask:ndarray/2/int · returned list · level recorded 2026-09-25
pad_np_bgr_image data_process/step1_get_bbox.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · faa0bfdfc22e317b · report fixture: signature np_image:ndarray/3/int, scale:float/0/float · returned tuple · level recorded 2026-09-24
polygon_to_mask data_process/demo_dataloader.py ran Apache-2.0 (permissive) · 989db0778a01d381 · report fixture: signature polygon:list/1/tuple, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
process_file in 33 papers data_process/step3-0_merge_json.py ran Apache-2.0 (permissive) · 8310d1132ebd9370 · report fixture: signature filename:str/0/str, folder_path:str/0/str, merged_data:dict/0/? · returned bool · level recorded 2026-09-25
process_file in 33 papers data_process/step4-0_merge_json.py ran Apache-2.0 (permissive) · 4a34cdc1b72ef759 · report fixture: signature filename:str/0/str, folder_path:str/0/str, merged_data:dict/0/? · returned bool · level recorded 2026-09-25
resize_long_side eval/get_naturalscore.py ran fingerprinted Apache-2.0 (permissive) · 351a3980dbd21561 · report fixture: signature image:ndarray/3/int, target_long:int/0/int · returned ndarray · level recorded 2026-09-25
run_aesthetic_laion eval/get_aesscore.py ran Apache-2.0 (permissive) · 4b36c781c4d2014d · report fixture: signature model:callable/0/?, image:Tensor/4/float · returned Tensor · level recorded 2026-09-25
save_json in 11 papers data_process/step1_get_bbox.py ran Apache-2.0 (permissive) · dd06d65d58671193 · report fixture: signature faces_info:dict/0/?, output_path:str/0/str, id_list:dict/0/?, frame_list:list/1/int, metadata:dict/0/? · returned dict · level recorded 2026-09-25
call_gpt in 17 papers data_process/step4-1_get_tag_api.py unverified Apache-2.0 (permissive) · b9566bb371805bec · report
generate_image_embeddings eval/get_nexusscore.py unverified Apache-2.0 (permissive) · 565fde010ddcbc97 · report

Tasks

Human-Domain Subject-to-VideoOpen-Domain Subject-to-VideoSingle-Domain Subject-to-VideoVideo Generation

Datasets

Introduced by this paper, per the archive.

OpenS2V-5MOpenS2V-Eval

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