A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment

Overture Maps Downloader simplifies geospatial data manipulation by integrating the powerful DuckDB, Dask DataFrames, and GDAL/OGR open source tools.

General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

[NeurIPS 2021 Spotlight] Learning to Compose Visual Relations

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

[ECCV 2022] Compositional Generation using Diffusion Models

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

[NeurIPS2022] Deep Model Reassembly

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

Grounded Segment Anything: From Objects to Parts

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

Official code for VisProg (CVPR 2023 Best Paper!)

Official Repository of ChatCaptioner

OpenAGI: When LLM Meets Domain Experts

A curated list of Composable AI methods: Building AI system by composing modules.

Segment Any RGBD

[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

A Data Streaming Library for Efficient Neural Network Training

Hydra is a framework for elegantly configuring complex applications

The friendly PIL fork

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

Emacs as your personal AI assistant. Use LLMs such as ChatGPT or LLaMA for text generation or DALL-E and Stable Diffusion for image generation. Also supports speech input / output.

Recreate any audio track by rearranging the frames of another video

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

The new All-in-One CFW package for the Nintendo Switch.