Official inference repo for FLUX.2 models

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

[arXiv 2025] Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Official implementation of ICML2025 paper "ToMA: Token Merge with Attention for Diffusion Models"

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

HunyuanVideo-1.5: A leading lightweight video generation model

OpenMMLab Pose Estimation Toolbox and Benchmark.

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

A curated list of egocentric (first-person) vision and related area resources

[Nips 2025] EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation

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

Get cookies.txt, NEVER send information outside.

A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.

Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"

ViPE: Video Pose Engine for Geometric 3D Perception

Export iMessage data + run iMessage Diagnostics

A sparse attention kernel supporting mix sparse patterns

FlashInfer: Kernel Library for LLM Serving

Tile primitives for speedy kernels

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Next-Token Prediction is All You Need

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Wan: Open and Advanced Large-Scale Video Generative Models

Official PyTorch Implementation for Dual-Process Image Generation, ICCV 2025

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