README.md

December 9, 2025 Β· View on GitHub

πŸ”₯ Awesome Personalized Video Creation

If you like our project, please give us a star ⭐ on GitHub for the latest update.

Awesome PRs Welcome GitHub Repo stars

This repository is dedicated to collecting, organizing, and tracking recent advancements in personalized video generation and editing. It serves as a centralized resource for papers, models, and benchmarks in this rapidly evolving field.

Table

πŸ“£ Update News

[2024-07-18] We have initiated the repository.

⚑ Contributing

If you want to add your work to this list, please do not hesitate to email jhuang90@ur.rochester.edu or pull requests. Markdown format:

* | [**Paper Title**] | Venue | Date | [[paper]](link) [[code]](link) [[project]](link)|

πŸ“š Preliminaries

πŸ“½οΈ Video Generation Foundation Models

πŸŒ€ Diffusion Transformer

πŸŒ€ U-Net

πŸŒ€ Autoregressive

πŸŽ›οΈ Multi-Modal Control Signal Tokenization

πŸ•³οΈ Control Paradigms in Video Generation

πŸ“Œ Structure-aware Control Modules

πŸ“Œ Parameter-efficient Adaptation

πŸ“Œ Localized Editing

🌐 Open-Domain Personalized Video Generation Models

🎨 Subject-Driven Video Generation Models

Test-time Fine-tuning

TitleVenueDateLinks
PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image ModelsCVPR 2024Dec 2023 (arXiv)Paper – Project - Code
VideoBooth: Diffusion-based Video Generation with Image PromptsCVPR 2024Dec 2023 (arXiv)Paper – Project – Code
CustomVideo: Customizing Text-to-Video Generation with Multiple SubjectsarXivJan 18 2024Paper – Project
DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial ControlACMMM 2024May 21 2024Paper – Project - Code
Still-Moving: Customized Video Generation without Customized Video DataTOGJul 11 2024Paper – Project
Customcrafter: Customized Video Generation with Preserving Motion and Concept Composition AbilitiesAAAI 2025Feb 2025Paper – Code
Dynamic Concepts Personalization from Single VideosSIGGRAPH 2025Feb 20 2025Paper – Page
BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity PropagationarXivMay 11 2025Paper

Pretrained Adaptation

TitleVenueDateLinks
Movie Gen: A Cast of Media Foundation ModelsarXivOct 17 2024Paper – Project
SUGAR: Subject-Driven Video Customization in a Zero-Shot MannerarXivDec 13 2024Paper – Project
VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion ModelsarXivDec 27 2024Paper – Code
Multi-subject Open-set Personalization in Video GenerationCVPR 2025Jan 2025 (arXiv)Paper – Project – Code
ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time TuningarXivJan 2025Paper
AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse GuidancearXivFeb 2025Paper – Code
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored PromptsCVPR 2025Feb 2025Paper
Phantom: Subject-Consistent Video Generation via Cross-Modal AlignmentICCV 2025Feb 16 2025Paper – Project – Code
SkyReels-A2: Compose Anything in Video Diffusion TransformersarXivApr 3 2025Paper – Project – Code
CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based GuidancearXivMar 13 2025Paper
MAGREF: Masked Guidance for Any-Reference Video GenerationarXivMay 29 2025Paper Code
Tora2: Motion and Appearance Customized DiffusionTransformer for Multi-Entity Video GenerationarXivJul 08 2025Paper
BindWeave: Subject-Consistent Video Generation via Cross-Modal IntegrationarXivOct 1 2025Paper Page
Kaleido: Open-Sourced Multi-Subject Reference Video Generation ModelarXivOct 21 2025Paper Code
First Frame Is the Place to Go for Video Content CustomizationarXivNov 19 2025Paper Code

πŸŽ₯ Motion-Driven Video Generation Models

TitleVenueDateLinks
Structure and Content-Guided Video Synthesis with Diffusion ModelsICCV 2023Feb 2023Paper
VideoComposer: Compositional Video Synthesis with Motion ControllabilityNeurIPS 2023Jun 2023 (arXiv)Paper – Project - Code
DreamVideo: Composing Your Dream Videos with Customized Subject and MotionCVPR 2024Dec 2023 (arXiv)Paper – Project - Code
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion ModelsECCV 2024Feb 2024Paper - Project - Code
MotionBooth: Motion-Aware Customized Text-to-Video GenerationNeurIPS 2024 (Spotlight)Jun 2024Paper - Project - Code
DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion ControlarXivOct 17 2024Paper – Page
MoTrans: Customized Motion Transfer with Text-driven Video Diffusion ModelsACMMM 2024Dec 2 2024Paper – Code
Subject-driven Video Generation via Disentangled Identity and MotionarXivApr 23 2025Paper – Code
DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video CustomizationarXivMar 4 2025Paper – Project
VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion ModelsCVPR 2025Mar 13 2025Paper Project
DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion AdaptationArxivMar 18 2025Paper - Project - Code
JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video GenerationarXivMar 31 2025Paper – Project
PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and EnhancementarXivJun 9 2025Paper
CoMo: Compositional Motion Customization for Text-to-Video GenerationarXivOct 27 2025Paper - Page
MotionStream: Real-Time Video Generation with Interactive Motion ControlsarXivNov 03 2025Paper - Page - [https://github.com/alex4727/motionstream]
MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion TransformerarXivDec 08 2025Paper

βœ‚οΈ Personalized Video Editing Models

TitleVenueDateLinks
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video GenerationICCV 2023Dec 22 2022Code
Paper
Dreamix: Video Diffusion Models are General Video EditorsarXivFeb 2023Paper – Project
Make-A-Protagonist: Generic Video Editing with Visual and Textual CluesarXivMay 15 2023Paper – Code
Towards Consistent Video Editing with Text-to-Image Diffusion ModelsNeurIPS 2023May 27 2023Paper
Make-Your-Video: Customized Video Generation Using Textual and Structural GuidanceTVCG 2024Jun 2023Paper – Code
MagicEdit: High-Fidelity and Temporally Coherent Video EditingarXivAug 28 2023Paper – Code - Page
Cut-and-Paste: Subject-Driven Video Editing with Attention ControlarXivNov 20 2023Paper – Code
DragVideo: Interactive Drag-style Video EditingECCV 2024Dec 3 2023Paper - Code
AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing TasksTMLR 2024Mar 21 2024Paper – Project – Code
ReVideo: Remake a Video with Motion and Content ControlNeurIPS 2024May 22 2024β€”
Paper - Project - Code
DIVE: Taming DINO for Subject-Driven Video EditingarXivDec 4 2024Paper – Project
DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single ImagearXivMar 13 2025Paper
Get In Video: Add Anything You Want to the VideoarXivMay 2025Project – Paper
Pix2Video: Video Editing using Image DiffusionICCV 2023Mar 22 2023Project – Paper
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion ControlarXivMar 28 2025Project – Paper
Lucy Edit: Open-Weight Text-Guided Video EditingarXivSep 18 2025Paper - Github
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer ModelsarXivSep 22 2025Paper - Project - Code
ContextFlow: Training-Free Video Object Editing via Adaptive Context EnrichmentarXivSep 22 2025Paper - Project - Code
EditVerse: Unifying Image and Video Editing and Generation with In-Context LearningarXivSep 24 2025Paper
IMAGEdit : Let Any Subject TransformarXivOct 01 2025Paper - Project - Code
InstructX: Towards Unified Visual Editing with MLLM GuidancearXivOct 10 2025Paper
In-Context Learning with Unpaired Clips for Instruction-based Video EditingarXivOct 16 2025Paper - Code

πŸ”₯ Look-Driven Video Generation Models

Look: The unified visual baseline of a pieceβ€”covering style, color, and lighting, texture/grade, and any VFX choices, to achieve a consistent on-screen feel.

TitleVenueDateLinks
VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context LearningarXivOct 29 2025Paper – Project – Code
Video-As-Prompt: Unified Semantic Control for Video GenerationarXivOct 28 2025Paper – Project – Code
Omni-Effects: Unified and Spatially-Controllable Visual Effects GenerationarXivAug 11 2025Paper – Project – Code
VFX Creator: Animated Visual Effect Generation with Controllable Diffusion TransformerarXivFeb 09 2025Paper – Project
StyleMaster: Stylize Your Video with Artistic Generation and TranslationCVPR 2025Dec 10 2024Paper – Project – Code

πŸ§‘ Human-Domain Personalized Video Generation Models

🎨 Identity-Driven Video Generation Models

Test-time Finetuning

TitleVenueDateLinks
Magic-Me: Identity-Specific Video Customized DiffusionarXivMar 20 2024Paper – Project – Code
ID-Animator: Zero-Shot Identity-Preserving Human Video GenerationarXivApr 23 2024Paper – Project – Code
PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic DegradationICCV 2025Mar 16 2025Paper – Project –Code
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video CustomizationarXivMar 16 2025Paper – Project –Code

Pretrained Adaptation

TitleVenueDateLinks
ConsisID: Identity-Preserving Text-to-Video Generation by Frequency DecompositionCVPR 2025Nov 26 2024Paper – Code
AnchorCrafter: Animate CyberAnchors Saling Your Products via Human-Object Interacting Video GenerationarXivNov 26 2024Paper – Code
Ingredients: Blending Custom Photos with Video Diffusion TransformersarXivJan 3 2025Paper – Code
Magic Mirror: ID-Preserved Video Generation in Video Diffusion TransformersICCV 2025Jan 7 2025Paper – Code
EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature FusionarXivJan 23 2025Paper – Code
SkyReels-A1: Expressive Portrait Animation in Video Diffusion TransformersarXivFeb 15 2025Paper – Page - Code
Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored PromptsCVPR 2025Feb 4 2025Paper – Page
FantasyID: Face Knowledge Enhanced ID-Preserving Video GenerationarXivFeb 25 2025Paper – Project – Code
Concat-ID: Towards Universal Identity-Preserving Video SynthesisarXivMar 18 2025Paper – Code
Proteus-ID: ID-Consistent and Motion-Coherent Video CustomizationarXivJun 30 2025Paper – Project
From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial ExpertsarXivAug 13 2025Paper - Code
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal ConditioningarXivSeq 10 2025Paper - Code - Page
Lynx: Towards High-Fidelity Personalized Video GenerationarXivSeq 19 2025Paper - Project
Stand-In: A Lightweight and Plug-and-Play Identity Control for Video GenerationarXivAug 12 2025Paper - Page - Code
Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement LearningarXivOct 17 2025Paper - Page - Code
ID-Composer: Multi-Subject Video Synthesis with Hierarchical Identity PreservationarXivNov 1 2025Paper
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video GenerationarXivDec 8 2025Paper - Github

Training-free

TitleVenueDateLinks
BachVid: Training-Free Video Generation with Consistent Background and CharacterarXivOct 24 2025Paper – Code
｜Scaling Zero-Shot Reference-to-Video Generation ｜ arXivDec 7 2025Paper - Code - Project｜

🎺 Audio-Driven Portrait Animation

TitleVenueDateLinks
EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak ConditionsECCV 2024Feb 27 2024Paper – Code – Page
EMO2: End-Effector Guided Audio-Driven Avatar Video GenerationECCV 2024Jan 18 2025Paper
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion SynthesisACMMM 2025Apr 07 2025Paper - Project - Code
Let Them Talk: Audio-Driven Multi-Person Conversational Video GenerationarXivMay 28 2025Paper – Project - Code
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion TransformersarXivJun 11 2025Paper – Project - Code
InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio ConditionsarXivJun 11 2025Paper – Project
OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body AnimationarXivJun 23 2025Paper – Project - Code
MirrorMe: Towards Realtime and High Fidelity Audio-Driven Halfbody AnimationarXivJun 27 2025Paper – Project
Democratizing High-Fidelity Co-Speech Gesture Video GenerationICCV 2025Jul 09 2025Paper – Project - Code
StableAvatar: Infinite-Length Audio-Driven Avatar Video GenerationarXivAug 11 2025Paper – Project - Code
FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait AnimationarXivAug 15 2025Paper - Project
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation SynthesisarXivSep 11 2025Paper - Project
Input-Aware Sparse Attention for Real-Time Co-Speech Video GenerationSiggrapha AsiaOct 2 2025Paper - Project - Code｜
Paper2Video: Automatic Video Generation from Scientific PapersarXivOct 6 2025Paper - Project - Code
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human AnimationarXivOct 27 2025Paper - Project - Code
Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward FeedbackAAAIOct 14 2025Paper - Project - Code

πŸ•Ί Pose-Driven Human Animation

TitleVenueDateLinks
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free VideosAAAI 2024Apr 3 2023Paper – Code – Page
DreamPose: Fashion Image-to-Video Synthesis via Stable DiffusionICCV 2023Apr 12 2023Paper – Code – Page
DisCo: Disentangled Control for Realistic Human Dance GenerationCVPR 2024Jun 30 2023Paper – Code – Page
MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware DiffusionICML 2024Nov 18 2023Paper – Code – Page
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion ModelCVPR 2024Nov 27 2023Paper – Code – Page
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character AnimationCVPR 2024Nov 28 2023Paper – Code – Page
Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose ControlarXivJun 05 2024Paper – Page
MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose GuidanceICML 2025Jun 28 2024Paper – Code – Page
MIMO: Controllable Character Video Synthesis with Spatial Decomposed ModelingCVPR 2025Sep 24 2024Paper – Code – Page
StableAnimator: High-Quality Identity-Preserving Human Image AnimationCVPR 2025Sep 24 2024Paper – Code – Page
DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D PosesICCV 2025Nov 30 2024Paper – Code – Page
DisPose: Disentangling Pose Guidance for Controllable Human Image AnimationICLR 2025Dec 12 2024Paper – Code - Page
Consistent Human Image and Video Generation with Spatially Conditioned DiffusionarXivDec 19 2024Paper – Code
DirectorLLM for Human-Centric Video GenerationarXivDec 19 2024Paper
X-Dyna: Expressive Dynamic Human Image AnimationCVPR 2025 (Highlight)Jan 17 2025Paper – Page - Code
HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video GenerationarXivFeb 7 2025Paper – Page
Animate Anyone 2: High-Fidelity Character Image Animation with Environment AffordancearXivFeb 10 2025Paper – Page
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid GuidancearXivApr 20 2025Paper – Page
TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video GenerationCVPR 2025Apr 11 2025Paper
DanceTogether! Identity-Preserving Multi-Person Interactive Video GenerationarXivMay 23 2025Paper – Page - Code
StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image AnimationarXivJul 20 2025Paper – Page
Wan-Animate: Unified Character Animation and Replacement with Holistic ReplicationarXivSeq 17 2025Paper – Page
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame PreservationarXivNov 24 2025Paper – Page - Code

🎨 Video-Driven Facial Reenactment

TitleVenueDateLinks
Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait AnimationSiggraph Asia 2024Jun 4 2024Paper - Page - Code
Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait AnimationIJCV 2025Seq 20, 2025Paper - Page - Code

πŸ’Ό Commercial Personalized Video Generation Models

πŸ“ˆ Datasets and Benchmarks

🌟 Personalized Video Generation Benchmarks

Title / BenchmarkVenueDateLinks
ConsisID-Bench – 150 identities & 90 prompts (human-domain)CVPR 2025 (Highlight)Nov 2024Project – Data
MSRVTT-Personalization (Alchemist-Bench) – Multi-subject personalization benchmarkCVPR 2025Jan 2025Paper – Data/Code
VACE-Benchmark – VACE: All-in-One Video Creation and EditingarXiv 2025Mar 2025Paper – Data/Code
FullBench - FullDiT: Multi-Task Video Generative Foundation Model with Full AttentionarXivMar 25 2025Paper – Data
A2 Bench – β€œElements-to-Video” evaluation benchmark for arbitrary subjectsarXivApr 2025Paper – Data/Code
OpenS2V-Eval – Fine-grained S2V benchmark (180 prompts, real & synthetic)arXivMay 28 2025Paper – Project – Code
Proteus-BencharXivJun 30 2025Paper – Project

πŸ“‚ Personalized Video Generation Datasets

Subject-to-Video Datasets

Title / DatasetVenueDateLinks
Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic DatasetArxivOct 2025Paper – Project – Data
ConsisID-DataCVPR 2025 (Highlight)Oct 2024Paper – Project – Data
Any2CapInsArxivMar 2025Paper – Project – Data
OpenS2V-5MArxivMay 28 2025Paper – Project – Data
Phantom-DataArxivJun 23 2025Paper – Project – Data
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human GenerationArxivJul 14 2025Paper – Project – Data
TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video GenerationArxivOct 8 2025Paper – Project – Data

ID-Driven Creation Datasets

Title / DatasetVenueDateLinks
TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head SynthesisArxiv 2025Aug 2025Paper – Project – Data
CustomConcept101CVPR 2023Dec 2023Paper – Project – Data

Multi-Subject Disambiguation

Title / DatasetVenueDateLinks
Character Mixing for Video GenerationArxiv 2025Oct 06 2025Paper – Project – Code

πŸ“ Key Evaluation Metrics

πŸ‘ Acknowledgement