📖 This is a repository for organizing papers, codes, and other resources related to personalized video generation and editing.

Official repository of In-Context LoRA for Diffusion Transformers

DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation

[CVPR 2026, CVEU] Official codebase for FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation

Video Diffusion Transformers are In-Context Learners

A collection of resources on personalized image generation.

[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)

[ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

The repository for the paper "Image Inversion: A Survey from GANs to Diffusion and Beyond".

official implementation of VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning (COLM 2024)

[ICLR 2025] Trajectory Attention For Fine-grained Video Motion Control

[WACV 2024] Training-Free Layout Control with Cross-Attention Guidance

[CVPR 2026] When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

Training-Free (Inversion-Free) methods meet WAN2.1-T2V🤗

Official PyTorch implementation of the paper "FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing"

[CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

Code for FreeTraj, a tuning-free method for trajectory-controllable video generation

[SIGGRAPH Asia 2024] TrailBlazer: Trajectory Control for Diffusion-Based Video Generation

Video Content Customization Using First Frame

The official repo for [TPAMI'23] "Vision Transformer with Quadrangle Attention"