[NeurIPS 2023] Continuous Parametric Optical Flow

[NeurIPS 2024] Official repository for downloading and using LAVIB

[ECCV2024 Oral] Clearer anytime frame interpolation & Manipulated interpolation of anything

Very simple flow-based programming framework.

A direct, pixel-level mapping from src to dst images via encoder-decoder. Supports, training, inference or export to VFX tools.

Official implementations for paper: VACE: All-in-One Video Creation and Editing

nk2dl (aka Nuke to Deadline). A python module for submitting nukescripts to Thinkbox Deadline

[CVPR 2025] RollingDepth: Video Depth without Video Models

Text Editor for Nk files inside Nuke

Segment Anything in High Quality [NeurIPS 2023]

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Elastic Training on Kubernetes

Kubeflow Deployment Manifests

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Highly extensible platform for developers to better understand the complexity of Kubernetes clusters.

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

CLI that makes it easy to create, test and deploy Airflow DAGs to Astronomer

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Professional player and review tool for vfx, animation and computer graphics.

The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"

Example of working with Airflow together with MLflow

The open source developer platform to build AI/LLM applications and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integra…

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

aim-mlflow integration

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Open Source ML Model Versioning, Metadata, and Experiment Management