Stars
Implementation of PSGD optimizer in JAX
[ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A multi-backend (TensorFlow, PyTorch, JAX, and NumPy) implementation of the Segment Anything model in Keras 3.0
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability
A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
A simple, performant and scalable Jax LLM!
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
Convert any music library into a music production sample-library with ML
Autoresize Textarea for Svelte apps using proxy element.
Exploring finetuning public checkpoints on filter 8K sequences on Pile
Automatically take good care of your preemptible TPUs