LongLive: Real-time Interactive Long Video Generation

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Youtu-GraphRAG boosts cost efficiency, inference accuracy, and cross-domain adaptability, pushing the boundaries of performance in complex QA.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

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

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.

Official inference repo for FLUX.1 models

Wan: Open and Advanced Large-Scale Video Generative Models

Enjoy the magic of Diffusion models!

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

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

丁真宇宙，一眼丁真合集，已有两千多张图片。The YYDZ (Yi Yan Ding Zhen / One Eye Ding Zhen) dataset.

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

A pytorch of the paper ''UNI-IQA: A Unified Approach for Mutual Promotion of Natural and Screen Content Image Quality Assessment"

SkyReels-A2: Compose anything in video diffusion transformers

DICE-Talk is a diffusion-based emotional talking head generation method that can generate vivid and diverse emotions for speaking portraits.

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Official repository for LTX-Video

Open-source and strong foundation image recognition models.

Wan: Open and Advanced Large-Scale Video Generative Models

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment