Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"

No fortress, purely open ground. OpenManus is Coming.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Wan: Open and Advanced Large-Scale Video Generative Models

FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation

[WWW 2025] Official PyTorch Code for "CTR-Driven Advertising Image Generation with Multimodal Large Language Models"

[arXiv'25] AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Pippo: High-Resolution Multi-View Humans from a Single Image

Benchmarking physical understanding in generative video models

Investigating CoT Reasoning in Autoregressive Image Generation

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Code for [CVPR 2024] VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence

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

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

Taming Stable Diffusion for Lip Sync!

[CVPR 2025] X-Dyna: Expressive Dynamic Human Image Animation