Pith. sign in

REVIEW 8 cited by

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.16498 v1 pith:LJT7KIYF submitted 2023-11-27 cs.CV cs.GR

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Zhongcong Xu , Jianfeng Zhang , Jun Hao Liew , Hanshu Yan , Jia-Wei Liu , Chenxu Zhang , Jiashi Feng , Mike Zheng Shou This is my paper
classification cs.CV cs.GR
keywords animationimagereferencevideotemporalmodelaimsappearance
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. Despite achieving reasonable results, these approaches face challenges in maintaining temporal consistency throughout the animation due to the lack of temporal modeling and poor preservation of reference identity. In this work, we introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity. To achieve this, we first develop a video diffusion model to encode temporal information. Second, to maintain the appearance coherence across frames, we introduce a novel appearance encoder to retain the intricate details of the reference image. Leveraging these two innovations, we further employ a simple video fusion technique to encourage smooth transitions for long video animation. Empirical results demonstrate the superiority of our method over baseline approaches on two benchmarks. Notably, our approach outperforms the strongest baseline by over 38% in terms of video fidelity on the challenging TikTok dancing dataset. Code and model will be made available.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

    cs.CV 2026-04 unverdicted novelty 7.0

    ExpertEdit edits novice motions to expert skill levels by learning a motion prior from unpaired videos and infilling masked skill-critical spans.

  2. Stylistic Attribute Control in Latent Diffusion Models

    cs.CV 2026-05 unverdicted novelty 6.0

    A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.

  3. Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

    cs.CV 2026-04 unverdicted novelty 6.0

    A new 140K-video dataset and native-scale Qwen2.5-VL detector for AI-generated videos that avoids preprocessing losses to retain high-frequency forgery artifacts.

  4. CameraCtrl: Enabling Camera Control for Text-to-Video Generation

    cs.CV 2024-04 unverdicted novelty 6.0

    CameraCtrl enables accurate camera pose control in video diffusion models through a trained plug-and-play module and dataset choices emphasizing diverse camera trajectories with matching appearance.

  5. TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation

    cs.CV 2026-07 conditional novelty 5.0

    Anchor-guided fixed-capacity multimodal memory plus stage-parallel few-step denoising stabilizes long-form causal audio-video digital humans at real-time speed.

  6. InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

    cs.CV 2026-07 unverdicted novelty 5.0

    InterCMDM proposes a block-causal latent diffusion framework with dual-stream causal transformers and multi-task attention masks for autoregressive text-conditioned two-person interaction generation and reports SOTA r...

  7. DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment

    cs.RO 2025-04 unverdicted novelty 5.0

    DriVerse is a generative model that simulates driving scenes from an image and trajectory using multimodal prompting and motion alignment, achieving better performance on nuScenes and Waymo datasets with minimal training.

  8. Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification

    cs.CV 2024-06 unverdicted novelty 5.0

    Pose-dIVE augments Re-ID training sets with diffusion-generated images of diverse poses and viewpoints by conditioning on SMPL parameters.