[CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel

Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

High-resolution models for human tasks.

WACV2022: Transfer Learning for Pose Estimation of Illustrated Characters

Enjoy the magic of Diffusion models!

一个简单好用的 spine 文件查看&导出&壁纸工具。A simple and easy-to-use spine file viewer & exporter & wallpaper.

🦴 Command-line tool for converting Spine skeleton data between different formats (skel/json) and different versions (3.5/3.6/3.7/3.8/4.0/4.1/4.2).

iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

AI agents running research on single-GPU nanochat training automatically

[ICML 2026] | Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory

[CVPR 2026] Official Implementation of Edit2Perceive

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Complete BIOS and firmware packs for RetroArch, Batocera, Recalbox, Lakka, RetroPie, EmuDeck, RetroBat, RetroDECK, RomM. Verified checksums, 6700+ files, 300+ emulators profiled from source code.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Compute FID scores with PyTorch.

Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Karras et al. (2022) diffusion models for PyTorch

Lightweight Image Video Action Generation Inference Framework

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

A Collection of Variational Autoencoders (VAE) in PyTorch.

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

OpenVLA: An open-source vision-language-action model for robotic manipulation.