MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Augment robotics demonstration datasets with different robots and viewpoints

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

Denoising Diffusion Implicit Models

High-Resolution Image Synthesis with Latent Diffusion Models

Denoising Diffusion Probabilistic Models

Lora traing script for Lightricks LTX-video

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Official implementation of "Data Scaling Laws in Imitation Learning for Robotic Manipulation"

PyTorch code and models for V-JEPA self-supervised learning from video.

Wan: Open and Advanced Large-Scale Video Generative Models

Kanana: Compute-efficient Bilingual Language Models

Official repository for LTX-Video

Inpaint anything using Segment Anything and inpainting models.

[RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

Stable Video Diffusion Training Code and Extensions.

This is a python library. Install with "python3 -m pip install rp" then run with "python3 -m rp"

Motion-Controllable Video Diffusion via Warped Noise

Official PyTorch implementation for NeurIPS 2024 paper: Prediction with Action.

Abseil Common Libraries (Python)

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

An example RLDS dataset builder for X-embodiment dataset conversion.

This Python library makes it easy to display images and videos in a notebook.