Papers › MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

31 May 2024arXiv:2405.20851archive 2025-07-28

Shurong Yang, Huadong Li, Juhao Wu, Minhao Jing, Linze Li, Renhe Ji, Jiajun Liang, Haoqiang Fan

Despite raw driving videos contain richer information on facial expressions than intermediate representations such as landmarks in the field of portrait animation, they are seldom the subject of research. This is due to two challenges inherent in portrait animation driven with raw videos: 1) significant identity leakage; 2) Irrelevant background and facial details such as wrinkles degrade performance. To harnesses the power of the raw videos for vivid portrait animation, we proposed a pioneering conditional diffusion model named as MegActor. First, we introduced a synthetic data generation framework for creating videos with consistent motion and expressions but inconsistent IDs to mitigate the issue of ID leakage. Second, we segmented the foreground and background of the reference image and employed CLIP to encode the background details. This encoded information is then integrated into the network via a text embedding module, thereby ensuring the stability of the background. Finally, we further style transfer the appearance of the reference image to the driving video to eliminate the influence of facial details in the driving videos. Our final model was trained solely on public datasets, achieving results comparable to commercial models. We hope this will help the open-source community.The code is available at https://github.com/megvii-research/MegFaceAnimate.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2405.20851")

Code

Syntology Ran 9 of 17 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 17 samples from 2 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

megvii-research/megactor officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
megvii-research/megfaceanimate 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

17 samples harvested; 9 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
7ran
8unverified

Licence: 0 of the 17 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

HWC3 megvii-research/megfaceanimate/controlnet_aux_lib/util.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · f9ec7d70add02b6f · report
get_2d_sincos_pos_embed megvii-research/megactor/animate/megactor-sigma/embeddings.py official repository ran Apache-2.0 (permissive) · 45f1cb4de58b3f3d · report
get_context_scheduler megvii-research/megfaceanimate/animate/context.py official repository ran Apache-2.0 (permissive) · d0e5d8aa76eec8a1 · report
get_total_steps megvii-research/megfaceanimate/animate/context.py official repository ran Apache-2.0 (permissive) · 859e29c1dc1b42e9 · report
make_noise_disk megvii-research/megfaceanimate/controlnet_aux_lib/util.py official repository ran Apache-2.0 (permissive) · cb55313c2e3ca6a8 · report
ordered_halving megvii-research/megfaceanimate/animate/context.py official repository ran fingerprinted Apache-2.0 (permissive) · ef55c657c8ef7120 · report
simulate_head_motion megvii-research/megfaceanimate/eval_audio.py official repository ran Apache-2.0 (permissive) · ee0d00edd4592e12 · report
train_collate_fn megvii-research/megfaceanimate/face_dataset.py official repository ran Apache-2.0 (permissive) · 8b497c21236ea29d · report
zero_module megvii-research/megfaceanimate/animate/motion_module.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 4719c763c53be3fe · report
get_2d_sincos_pos_embed_from_grid megvii-research/megactor/animate/megactor-sigma/embeddings.py official repository unverified Apache-2.0 (permissive) · 59fa7b38de05f443 · report
get_clip_frames megvii-research/megfaceanimate/_preprocess.py official repository unverified Apache-2.0 (permissive) · 1db2c40c2d2bd67b · report
get_packed_frames megvii-research/megfaceanimate/_preprocess.py official repository unverified Apache-2.0 (permissive) · f350ab376ca5e41c · report
get_packed_frames megvii-research/megfaceanimate/_preprocess.py official repository unverified Apache-2.0 (permissive) · 1dd5f2925621c29e · report
get_timestep_embedding megvii-research/megactor/animate/megactor-sigma/embeddings.py official repository unverified Apache-2.0 (permissive) · 38f69a3d1e46016d · report
nms megvii-research/megfaceanimate/controlnet_aux_lib/util.py official repository unverified Apache-2.0 (permissive) · 6cce57d1077b8c49 · report
torch_dfs megvii-research/megactor/animate/megactor-sigma/stable_diffusion_controlnet_reference.py official repository unverified Apache-2.0 (permissive) · e55f24470648724c · report
zero_module megvii-research/megactor/animate/megactor-sigma/controlnet.py official repository unverified Apache-2.0 (permissive) · da94debb8019ad46 · report

Tasks

Portrait AnimationStyle TransferSynthetic Data Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPDiffusion

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