Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Turns Data and AI algorithms into production-ready web applications in no time.

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

NCCL Tests

Open-Sora: Democratizing Efficient Video Production for All

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

openFACS : an open source FACS-based 3D face animation system

Official code Cross-Covariance Image Transformer (XCiT)

A Gradio web UI for Large Language Models.

Official codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

🔥🔥 Deep Learning Head Pose Estimation using PyTorch.

StyleSwap: Style-Based Generator Empowers Robust Face Swapping (ECCV 2022)

Huggingface-compatible SDXL Unet implementation that is readily hackable

Dataset processing scripts for large-scale 3D human pose estimation

👁️ Facial Landmark Annotation Tool with OpenCV

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

A pytorch port of google-research/google-research/robust_loss/

A LARS implementation in PyTorch

Using modified BiSeNet for face parsing in PyTorch

Source code for CVPR 2020 paper "Deep Facial Non-Rigid Multi-View Stereo"

Official Code for Face Relighting with Geometrically Consistent Shadows (CVPR 2022)

Official implementation of IADB (Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model), published at Siggraph 2023.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset