Papers › FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

7 Feb 2025arXiv:2502.05179archive 2025-07-28

Shilong Zhang, Wenbo Li, Shoufa Chen, Chongjian Ge, Peize Sun, Yida Zhang, Yi Jiang, Zehuan Yuan, Binyue Peng, Ping Luo

DiT diffusion models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content and motion fidelity aligned with text prompts, however, often require large model parameters and a substantial number of function evaluations (NFEs). Realistic and visually appealing details are typically reflected in high resolution outputs, further amplifying computational demands especially for single stage DiT models. To address these challenges, we propose a novel two stage framework, FlashVideo, which strategically allocates model capacity and NFEs across stages to balance generation fidelity and quality. In the first stage, prompt fidelity is prioritized through a low resolution generation process utilizing large parameters and sufficient NFEs to enhance computational efficiency. The second stage establishes flow matching between low and high resolutions, effectively generating fine details with minimal NFEs. Quantitative and visual results demonstrate that FlashVideo achieves state-of-the-art high resolution video generation with superior computational efficiency. Additionally, the two-stage design enables users to preview the initial output before committing to full resolution generation, thereby significantly reducing computational costs and wait times as well as enhancing commercial viability .

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="2502.05179")

Code

Syntology Ran 6 of 15 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · violated contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

foundationvision/flashvideo officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

15 samples harvested; 6 ran; 1 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · violated contract
1ran · our draft was wrong
1ran
9unverified

Licence: 0 of the 15 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 foundationvision/flashvideo. “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.

cast_tuple foundationvision/flashvideo/flashvideo/vae_modules/cp_enc_dec.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · c1b68cdd9e73316a · report
default foundationvision/flashvideo/flashvideo/vae_modules/attention.py official repository ran · violated contract Apache-2.0 (permissive) · 424012cb37b31172 · report
divisible_by foundationvision/flashvideo/flashvideo/vae_modules/cp_enc_dec.py official repository ran · violated contract fingerprinted Apache-2.0 (permissive) · f912c209e9c899ca · report
exists foundationvision/flashvideo/flashvideo/vae_modules/attention.py official repository ran · violated contract Apache-2.0 (permissive) · aa5486a3650902d8 · report
get_unique_embedder_keys_from_conditioner foundationvision/flashvideo/flashvideo/utils.py official repository ran Apache-2.0 (permissive) · 6686c8acf02ec831 · report
uniq foundationvision/flashvideo/flashvideo/vae_modules/attention.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 9a299fe5ae09e407 · report
add_extra_config_args foundationvision/flashvideo/flashvideo/arguments.py official repository unverified Apache-2.0 (permissive) · 96d9af18b865527c · report
add_model_config_args foundationvision/flashvideo/flashvideo/arguments.py official repository unverified Apache-2.0 (permissive) · 165540c4cfc6fce1 · report
add_sampling_config_args foundationvision/flashvideo/flashvideo/arguments.py official repository unverified Apache-2.0 (permissive) · 63a18d6c97fa3300 · report
decode foundationvision/flashvideo/flashvideo/utils.py official repository unverified Apache-2.0 (permissive) · c0aeee5806437317 · report
get_2d_sincos_pos_embed foundationvision/flashvideo/flashvideo/dit_video_concat.py official repository unverified Apache-2.0 (permissive) · cdd29f549144d05e · report
get_2d_sincos_pos_embed_from_grid foundationvision/flashvideo/flashvideo/dit_video_concat.py official repository unverified Apache-2.0 (permissive) · 665d8a4e8f673a4c · report
get_3d_sincos_pos_embed foundationvision/flashvideo/flashvideo/dit_video_concat.py official repository unverified Apache-2.0 (permissive) · 7759e9a501ea471a · report
get_batch foundationvision/flashvideo/flashvideo/utils.py official repository unverified Apache-2.0 (permissive) · 1bd867ae3eda28ff · report
is_odd foundationvision/flashvideo/flashvideo/vae_modules/cp_enc_dec.py official repository unverified Apache-2.0 (permissive) · 945442cc2f6a19c9 · report

Tasks

Computational EfficiencyText-to-Video GenerationVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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