Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

Official PyTorch implementation for "Large Language Diffusion Models"

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation

UniVideo: Unified Understanding, Generation, and Editing for Videos

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Official codes for the paper "GARDO: Reinforcing Diffusion Models without Reward Hacking"

DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

Scalable and memory-optimized training of diffusion models

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Official code for StoryMem: Multi-shot Long Video Storytelling with Memory

Official repo for UAE

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Orient Anything V2, NeurIPS 2025 Spotlight

Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]

Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

Code release for https://wonderzoom.github.io/

The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"

Mixture-of-Groups Attention for End-to-End Long Video Generation

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

LongLive: Real-time Interactive Long Video Generation

Official implementation of "MV-TAP: Tracking Any Point in Multi-View Videos"

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation