Papers › ModelScope Text-to-Video Technical Report

ModelScope Text-to-Video Technical Report

12 Aug 2023arXiv:2308.06571archive 2025-07-28

Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, Shiwei Zhang

This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and smooth movement transitions. The model could adapt to varying frame numbers during training and inference, rendering it suitable for both image-text and video-text datasets. ModelScopeT2V brings together three components (i.e., VQGAN, a text encoder, and a denoising UNet), totally comprising 1.7 billion parameters, in which 0.5 billion parameters are dedicated to temporal capabilities. The model demonstrates superior performance over state-of-the-art methods across three evaluation metrics. The code and an online demo are available at https://modelscope.cn/models/damo/text-to-video-synthesis/summary.

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 16 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

exponentialml/text-to-video-finetuning officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 11 ran (0 instrument-failed) · 5 unverified report
ali-vilab/VGen mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VideoLCM: Video Latent Consistency Model (arXiv:2312.09109; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ali-vilab/i2vgen-xl mentioned on GitHubpytorchSyntology: not harvested report
picsart-ai-research/streamingt2v mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (arXiv:2403.14773; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yhZhai/mcm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Motion Consistency Model: Accelerating Video Diffusion with Disentangled... (arXiv:2406.06890; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
5unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 exponentialml/text-to-video-finetuning. “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.

exponentialml/text-to-video-finetuning official repository 16 samples, 11 ran (0 instrument-failed) · 5 unverified
convert_text_enc_state_dict utils/convert_diffusers_to_original_ms_text_to_video.py ran MIT (permissive) · a59539766c1c5a5a · report fixture: signature text_enc_dict:dict/0/? · returned dict · level recorded 2026-09-24
convert_text_enc_state_dict_v20 utils/convert_diffusers_to_original_ms_text_to_video.py ran MIT (permissive) · 8d4b0c9f8b9a884e · report fixture: signature text_enc_dict:dict/0/? · returned dict · level recorded 2026-09-24
download_progress utils/lama.py ran MIT (permissive) · bfdb56f5b6ab8034 · report fixture: signature t:MockProgressBar/0/? · returned function · level recorded 2026-09-24
filter_dict in 5 papers utils/lora_handler.py ran MIT (permissive) · 9191602362628ded · report fixture: signature _dict:dict/0/?, keys:list/1/str · returned dict · level recorded 2026-09-24
get_bucket_sizes utils/bucketing.py ran MIT (permissive) · 8ff113de21fb6bc2 · report fixture: signature size:int/0/int, direction:str/0/str, min_size:int/0/int · returned list · level recorded 2026-09-24
get_prompt_ids utils/dataset.py ran MIT (permissive) · 6f7c993202e44dda · report fixture: signature prompt:str/0/str, tokenizer:callable/0/? · returned Tensor · level recorded 2026-09-24
is_video models/unet_3d_blocks.py ran MIT (permissive) here; the stored copy is pointer only · c1232f9d1e7794e4 · report fixture: signature num_frames:int/0/int, only_video:bool/0/bool · returned bool · level recorded 2026-09-24
min_res utils/bucketing.py ran fingerprinted MIT (permissive) · 40775842d99a25f9 · report fixture: signature size:int/0/int, min_size:int/0/int · returned int · level recorded 2026-09-24
normalize_input utils/dataset.py ran MIT (permissive) · dbfc36f5a5a5a1fd · report fixture: signature item:Tensor/4/int, mean:list/1/float, std:list/1/float, use_simple_norm:bool/0/bool · returned Tensor · level recorded 2026-09-24
read_caption_file utils/dataset.py ran MIT (permissive) · 00090fcbdd45d352 · report fixture: signature caption_file:str/0/str · returned str · level recorded 2026-09-24
up_down_bucket utils/bucketing.py ran fingerprinted MIT (permissive) · bec7ef14686681c0 · report fixture: signature m_size:int/0/int, in_size:int/0/int, direction:str/0/str · returned int · level recorded 2026-09-24
convert_unet_state_dict utils/convert_diffusers_to_original_ms_text_to_video.py unverified MIT (permissive) · 754cea3454b8b8da · report
inject_inferable_lora utils/lora.py unverified MIT (permissive) · df1f737e7e9ec97f · report
inject_trainable_lora in 12 papers utils/lora.py unverified MIT (permissive) · da50048edb81475c · report
inject_trainable_lora_extended in 11 papers utils/lora.py unverified MIT (permissive) · 929d4d45fed75939 · report
inpaint_watermark utils/lama.py unverified MIT (permissive) · 3c2dce662245aae1 · report

Tasks

DenoisingImage GenerationText-to-Video Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Video Generation MSR-VTT ModelScopeT2V CLIPSIM 0.2930 #9 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT ModelScopeT2V FID 11.09 #9 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT ModelScopeT2V FVD 550 #9 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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