Papers › DeepFaceLab: Integrated, flexible and extensible face-swapping framework

DeepFaceLab: Integrated, flexible and extensible face-swapping framework

12 May 2020arXiv:2005.05535archive 2025-07-28

Ivan Perov, Daiheng Gao, Nikolay Chervoniy, Kunlin Liu, Sugasa Marangonda, Chris Umé, Mr. Dpfks, Carl Shift Facenheim, Luis RP, Jian Jiang, Sheng Zhang, Pingyu Wu, Bo Zhou, Weiming Zhang

Deepfake defense not only requires the research of detection but also requires the efforts of generation methods. However, current deepfake methods suffer the effects of obscure workflow and poor performance. To solve this problem, we present DeepFaceLab, the current dominant deepfake framework for face-swapping. It provides the necessary tools as well as an easy-to-use way to conduct high-quality face-swapping. It also offers a flexible and loose coupling structure for people who need to strengthen their pipeline with other features without writing complicated boilerplate code. We detail the principles that drive the implementation of DeepFaceLab and introduce its pipeline, through which every aspect of the pipeline can be modified painlessly by users to achieve their customization purpose. It is noteworthy that DeepFaceLab could achieve cinema-quality results with high fidelity. We demonstrate the advantage of our system by comparing our approach with other face-swapping methods.For more information, please visit:https://github.com/iperov/DeepFaceLab/.

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="2005.05535")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: community (archive-listed): 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

22 repositories listed; official and paper-mentioned ones first.

iperov/DeepFaceLab officialmentioned in papermentioned on GitHubtfGPL-3.0 report
deepfakes/faceswap mentioned in papertfGPL-3.0 report
AbhinavBaranwal/DeepFaceLab mentioned on GitHubtfGPL-3.0 report
Adityaraj975/DFL mentioned on GitHubtfGPL-3.0 report
Adityaraj975/DeepFaceLab mentioned on GitHubtfGPL-3.0 report
IanSullivan/DeepFakeTorch mentioned on GitHubpytorchMIT report
JanFschr/DeepFaceLabTest mentioned on GitHubtfGPL-3.0 report
RoninTheKid/yessir mentioned on GitHubtfGPL-3.0 report
TangrisJones/AI-dfa mentioned on GitHubtfGPL-3.0 report
XuRen20/deepface mentioned on GitHubtfGPL-3.0 report
bellsrik86/DeepFaceLab mentioned on GitHubtfGPL-3.0 report
beskal80/KHAIREPO mentioned on GitHubtfGPL-3.0 report
big-bombom/deepfake mentioned on GitHubtfGPL-3.0 report
hectorgie/DeepFaceLab mentioned on GitHubtf report
huawenwei4/dfl mentioned on GitHubtfGPL-3.0 report
kukico/learning mentioned on GitHubtf report
mflames0327/DF-MOUTH mentioned on GitHubtfGPL-3.0 report
mrv8x/DeepFaceLab mentioned on GitHubtfGPL-3.0 report
onwan946/DeepFaceLab mentioned on GitHubtfGPL-3.0 report
respectableupstandinggentleman/test mentioned on GitHubtfnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
yfsin/deepfake_pro mentioned on GitHubtfGPL-3.0 report
yuemenglong/deep-learning-copy mentioned on GitHubtfGPL-3.0 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

7 samples harvested; 2 ran; 2 honoured the contract we drafted; 5 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.

2ran · honoured contract
5unverified

Licence: 0 of the 7 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 IanSullivan/DeepFakeTorch. “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.

create_window IanSullivan/DeepFakeTorch/SSIM.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 6154e3744ece5728 · report
gaussian IanSullivan/DeepFakeTorch/SSIM.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report
applyAffineTransform IanSullivan/DeepFakeTorch/faceswap.py community (archive-listed) unverified MIT (permissive) · b969fe757cf9f7ff · report
readPoints IanSullivan/DeepFakeTorch/faceswap.py community (archive-listed) unverified MIT (permissive) · 1dcdeb11977275df · report
rectContains IanSullivan/DeepFakeTorch/faceswap.py community (archive-listed) unverified MIT (permissive) · 3efc631de96ab804 · report
ssim IanSullivan/DeepFakeTorch/SSIM.py community (archive-listed) unverified MIT (permissive) · 9151c793f90473f0 · report
transfer IanSullivan/DeepFakeTorch/writes_images.py community (archive-listed) unverified MIT (permissive) · 288625cc2624100b · report

Tasks

Face Swapping

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Swapping FaceForensics++ DeepFaceLab SSIM 0.73 #1 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFaceLab landmarks 0.73 #1 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFaceLab perceptual loss 0.39 #1 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFaceLab pose 1.12 #1 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFaceLab verification 0.61 #1 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFakes SSIM 0.71 #10 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFakes landmarks 1.15 #10 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFakes perceptual loss 0.41 #10 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFakes pose 4.75 #10 of 17 Archive leaderboard report
Face Swapping FaceForensics++ DeepFakes verification 0.69 #10 of 17 Archive leaderboard report
Face Swapping FaceForensics++ Nirkin et al. SSIM 0.65 #11 of 17 Archive leaderboard report
Face Swapping FaceForensics++ Nirkin et al. landmarks 0.35 #11 of 17 Archive leaderboard report
Face Swapping FaceForensics++ Nirkin et al. perceptual loss 0.5 #11 of 17 Archive leaderboard report
Face Swapping FaceForensics++ Nirkin et al. pose 6.01 #11 of 17 Archive leaderboard report
Face Swapping FaceForensics++ Nirkin et al. verification 0.66 #11 of 17 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