Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

Build AI-powered applications with React, Svelte, Vue, and Solid

whiteboard / infinite canvas SDK

Beautifully designed components that you can copy and paste into your apps. Accessible. Customizable. Open Source.

An opinionated collection of components, hooks, and utilities for your Next.js project.

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Official implementations for paper: Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Official code for the paper "StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control."

Lifting ControlNet for Generalized Depth Conditioning

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

Love, Death & React

A growing curation of Text-to-3D, Diffusion-to-3D works.

A simple canvas drawing web app with responsive UI. Made with TypeScript, React, and Next.js.

Python library for video editing, presentation video generation, motion graphics, shader art coding, and other video production tasks

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.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Create a draggable and resizable dashboard in Streamlit, featuring Material UI widgets, Monaco editor (Visual Studio Code), Nivo charts, and more!

[ECCV 2022] Meta-Sampler: Almost Universal yet Task-Oriented Sampling for Point Clouds

High-Resolution Image Synthesis with Latent Diffusion Models

Dash Component wrapping React-Player

[AAAI 2022] Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction

Learn by experimenting on state-of-the-art machine learning models and algorithms with Jupyter Notebooks.

Try out deep learning models online on Google Colab

TikTok Scraper. Download video posts, collect user/trend/hashtag/music feed metadata, sign URL and etc.

Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

Google Research

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

Experimental CartoonGAN (Chen et.al.) implementation for quicker background generation for posters and new episodes

(NeurIPS 2020 oral) Code for "Deep Transformation-Invariant Clustering" paper