Highlights
- Pro
Stars
Official implementation of "MiraGe: Editable 2D Images using Gaussian Splatting"
Corpus to accompany: "Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding"
Ultra-minimal autoregressive diffusion model for image generation
[ICLR 2023] Factorized Fourier Neural Operators
An extremely fast Python package and project manager, written in Rust.
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
Autoregressive Model Beats Diffusion: π¦ Llama for Scalable Image Generation
Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Build terminal user interfaces and dashboards using Rust
Beautiful, minimal, opinionated CLI prompts inspired by the Clack NPM package
A Python library for selecting an item from a multi-field data list in terminal.
A simple terminal SSH manager that provides you with an easy access to the list of your favorite SSH servers. Binaries included! π
Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)
π· Reactive python package for managing, creating and visualizing different deep-learning image annotation formats
[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
[CVPR 2024 π₯] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
Vector (and Scalar) Quantization, in Pytorch
[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
Conversions of Fairseq models in HuggingFace-style
Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models