Stars
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
1K resolution vision transformers pretrained on 1B human images.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A library to fastly decode video with ffmpeg and rust
Tiny AutoEncoder for Hunyuan Video (and other video models)
MotionStream: Real-Time Video Generation with Interactive Motion Controls
[CVPR 2025] Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning
Vector (and Scalar) Quantization, in Pytorch
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
Shapley Interactions and Shapley Values for Machine Learning
This repo contains the code for 1D tokenizer and generator
Official repository for our work on micro-budget training of large-scale diffusion models.
Recaption large (Web)Datasets with vllm and save the artifacts.
[Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models
Open Public Transport Digital Twin (OPDTwin)
Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
The best OSS video generation models, created by Genmo
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
Easily switch between windows of the same app with Alt+` (Backtick), also switch between apps with Alt+Tab.
A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model
LPIPS metric. pip install lpips
A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]
[ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
Browser extension that generates API specs for any app or website