Stars
We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…
Scaleway Serverless Functions (FaaS) framework to increase developer experience, local testing and more
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…
Bringing Old Photo Back to Life (CVPR 2020 oral)
Swift app demonstrating Core ML Stable Diffusion
"GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimates", WACV 2023
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
macOS: mount any linux-supported filesystem read/write using NFS and a microVM
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
Precompiled OpenCV 4.3.0 to JavaScript + WebAssembly for node and deno. 🦕
Gender,Age,Face detection using opencv and caffe model
lambda-go-api-proxy makes it easy to port APIs written with Go frameworks such as Gin (https://gin-gonic.github.io/gin/ ) to AWS Lambda and Amazon API Gateway.
Image annotation tool for CreateML. Uses SwiftUI.
An open-source AI agent that brings the power of Gemini directly into your terminal.
volkszaehler / libsml
Forked from dailab/libsmlImplementation in C of the Smart Message Language (SML) protocol
Repository for technical resources
Golang implementation of the Raft consensus protocol
Performant and reusable text view component (TextKit 2), with line numbers and more. UITextView / NSTextView replacement.
Chat with Apple Intelligence using the Foundation Models Framework
Tool to download IPv4 and IPv6 ranges of CDN providers for bug bounties