function: image-processing
4273 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| openai/glide-text2im Official codebase for GLIDE, a diffusion-based text-conditional image synthesis model from OpenAI. It provides pretrained models and notebo… | 10 | 3684 | maintenance |
| lolishinshi/imsearch A Rust-based large-scale similar image search tool that uses feature point matching (ORB features with a FAISS-style index) to find full im… | 94 | 1074 | active |
| facebookresearch/hiera Hiera is the official PyTorch implementation of a hierarchical vision transformer from Meta AI (ICML 2023 Oral). It achieves state-of-the-a… | 20 | 1074 | active |
| CoderZhuXH/XHLaunchAd XHLaunchAd is an Objective-C library for iOS that provides a complete launch/splash screen advertising solution. It supports static and ani… | 23 | 3679 | maintenance |
| ARM-software/CMSIS-DSP CMSIS-DSP is ARM's optimized embedded compute library providing DSP and math kernels for Cortex-M and Cortex-A processors, including FFT, f… | 96 | 1073 | stable |
| facebookresearch/CutLER CutLER is a research codebase from Meta FAIR for training object detection and instance segmentation models without human annotations, usin… | 66 | 1072 | active |
| AILab-CVC/UniRepLKNet UniRepLKNet is a large-kernel ConvNet architecture (CVPR 2024, TPAMI 2025) that provides universal perception across image, audio, video, p… | 43 | 1072 | stable |
| straker/kontra Kontra.js is a lightweight JavaScript gaming micro-library optimized for size-constrained contexts like the js13kGames competition. It prov… | 52 | 1071 | active |
| itorr/eva-title A web-based Evangelion title card generator that renders custom text in the style of the classic 1995 Neon Genesis Evangelion episode title… | 49 | 1071 | active |
| Mindwerks/worldengine WorldEngine is a Python-based procedural world generator that simulates plate tectonics, erosion, rain shadows, and Holdridge life zones to… | 73 | 1070 | active |
| yeates/PromptFix PromptFix is a PyTorch implementation of a diffusion-model-based image restoration model that follows natural language instructions to fix … | 24 | 1070 | active |
| ototadana/sd-face-editor A Stable Diffusion Web UI extension that detects and regenerates faces in generated images to fix broken faces, change facial expressions, … | 23 | 1070 | active |
| jeffbass/imagezmq imageZMQ is a set of Python classes that transport OpenCV images between computers using PyZMQ messaging. It enables distributed computer v… | 62 | 1069 | stable |
| TrueMyst/BeatPrints BeatPrints is a Python library and CLI that generates eye-catching, Pinterest-style posters for music tracks and albums. It integrates with… | 85 | 1068 | active |
| luxonis/depthai DepthAI is Luxonis's Python library and SDK for developing with Luxonis OAK camera hardware, enabling spatial AI and computer vision on emb… | 65 | 1068 | active |
| dimartarmizi/map-to-poster MapToPoster JS is a client-side web application that turns any global location into a high-resolution, customizable map poster. It offers t… | 54 | 1068 | active |
| Fannovel16/ComfyUI-Frame-Interpolation A set of custom nodes for ComfyUI that perform video frame interpolation using models like RIFE, FILM, GMFSS, and others. It lets users gen… | 52 | 1068 | active |
| Stability-AI/stable-point-aware-3d SPAR3D is Stability AI's open-source model for fast single-image 3D mesh reconstruction using a two-stage pipeline with point cloud conditi… | 30 | 1068 | active |
| you-apps/WallYou Wall You is a privacy-focused Android wallpaper app built with Kotlin and Material Design 3. It lets users browse, download, filter, and au… | 91 | 1067 | active |
| tomayac/SVGcode SVGcode is a Progressive Web App that converts raster images (JPG, PNG, GIF, WebP, AVIF, etc.) into SVG vector graphics. It runs in the bro… | 70 | 1066 | active |
| hujie-frank/SENet Official Caffe/CUDA implementation of Squeeze-and-Excitation Networks (SENet), channel-attention building blocks for convolutional neural n… | 32 | 3646 | maintenance |
| rafael-fuente/diffractsim A flexible Python library for simulating and visualizing diffraction and physical optics phenomena using scalar diffraction techniques like… | 65 | 1065 | active |
| LAStools/LAStools LAStools is a collection of efficient, scriptable C++ command-line tools for processing LiDAR point cloud data in ASPRS LAS and compressed … | 82 | 1064 | active |
| 0-RTT/telegraph A serverless image, video, and file hosting service built on Cloudflare Workers and Pages, storing files via the Telegram Bot API with meta… | 68 | 1064 | active |
| op7418/guizang-material-illustration A Claude Code / Codex agent skill that generates material-style illustrations with Chinese labels for articles, notes, charts, and teaching… | 54 | 1064 | active |
| lucidrains/mlp-mixer-pytorch A PyTorch implementation of Google AI's MLP-Mixer, an all-MLP architecture for image classification that uses neither convolutions nor atte… | 48 | 1064 | active |
| fossasia/magic-epaper-app Magic ePaper is an open-source Flutter mobile app for designing content and transferring it to battery-free NFC ePaper badges. It offers dr… | 77 | 1063 | active |
| rust-cv/cv Rust CV is a mono-repo of pure-Rust computer vision crates aiming to encapsulate capabilities of OpenCV, OpenMVG, and vSLAM frameworks in c… | 47 | 1063 | active |
| vijishmadhavan/ArtLine ArtLine is a deep learning project that converts portrait photos into line art portraits, with a ControlNet-based variant that adjusts styl… | 32 | 3630 | maintenance |
| NVlabs/SegFormer Official PyTorch implementation of SegFormer, a transformer-based semantic segmentation framework with a hierarchical encoder and lightweig… | 32 | 3629 | maintenance |
| mittagessen/kraken kraken is a turn-key OCR/HTR engine built on neural networks, optimized for historical and non-Latin script material. It provides trainable… | 99 | 1061 | active |
| neka-nat/cupoch Cupoch is a C++/Python library that implements rapid 3D data processing for robotics using CUDA, based on Open3D. It provides GPU-accelerat… | 63 | 1061 | active |
| devilsen/CZXing CZXing is a C++ port of ZXing for Android that provides WeChat-level QR code and barcode scanning, including WeChat's detection and super-r… | 55 | 1060 | active |
| darkmoonight/Rain Rain is a feature-rich, open-source weather application built with Flutter for Android. It offers current conditions, hourly and 12-day for… | 93 | 1059 | active |
| leggedrobotics/elevation_mapping_cupy A GPU-accelerated elevation mapping library for robotics, built on CuPy and integrated with ROS, that fuses point clouds into multi-modal t… | 89 | 1059 | active |
| clovaai/stargan-v2 The official PyTorch implementation of StarGAN v2, a CVPR 2020 paper on diverse image-to-image translation across multiple domains using a … | 32 | 3617 | maintenance |
| sb-ai-lab/EmotiEffLib EmotiEffLib (formerly HSEmotion) is a lightweight library for facial emotion and engagement recognition in photos and videos, available in … | 65 | 1057 | active |
| yoyo-nb/Thin-Plate-Spline-Motion-Model The official PyTorch implementation of the CVPR 2022 paper 'Thin-Plate Spline Motion Model for Image Animation'. It animates a source image… | 32 | 3604 | maintenance |
| hnvn/flutter_image_cropper A Flutter plugin that provides image cropping and rotation on Android, iOS, and Web by wrapping native libraries (uCrop, TOCropViewControll… | 75 | 1055 | active |
| craftyjs/Crafty Crafty is an open-source JavaScript/HTML5 game engine built around an entity-component-system architecture. It provides components for 2D g… | 23 | 3602 | maintenance |
| rossmoody/svg-gobbler SVG Gobbler is an open-source browser extension for Chrome and Firefox that finds, optimizes, edits, and exports SVG content from any webpa… | 89 | 1051 | active |
| url-kaist/patchwork-plusplus Patchwork++ is a fast, robust, and self-adaptive ground segmentation algorithm for 3D LiDAR point clouds, published at IROS 2022. It provid… | 87 | 1051 | active |
| williamyang1991/VToonify Official PyTorch implementation of VToonify, a SIGGRAPH Asia 2022 framework for controllable high-resolution portrait video style transfer … | 32 | 3584 | maintenance |
| psoho/fast-poster fastposter is a self-hostable poster/image generation service with a drag-and-drop web editor for composing text, images, QR codes, and ava… | 32 | 1050 | active |
| keijiro/Skinner Skinner is a Unity library of special effects that use the vertices of an animating skinned mesh as emitting points for particle and trail … | 23 | 3581 | maintenance |
| drprojects/superpoint_transformer Official PyTorch implementation of Superpoint Transformer (ICCV'23), SuperCluster (3DV'24), and EZ-SP (ICRA'26) for efficient semantic and … | 64 | 1049 | active |
| megamarc/Tilengine Tilengine is a free, open-source, cross-platform 2D graphics engine written in portable C99 for creating classic/retro-style games with til… | 77 | 1048 | active |
| qqlu/Entity EntitySeg is an open-source PyTorch toolbox for open-world, high-quality image segmentation, built on Detectron2. It aggregates multiple re… | 32 | 1048 | active |
| anuragxel/salt SALT is a Python-based image labeling tool built on Meta AI's Segment Anything Model, providing a barebones GUI for annotating images with … | 30 | 1048 | active |
| addyosmani/squish Squish is a browser-based batch image compression tool that uses WebAssembly codecs to compress and convert images entirely client-side. It… | 22 | 1048 | active |
| zhbhun/idify Idify is a browser-based application for creating ID, passport, and visa photos with all processing done locally in the browser. It require… | 56 | 1047 | active |
| kikoso/android-stackblur An Android library that applies a StackBlur (gaussian-like) blur effect to Bitmaps with configurable radius or gradient. It offers Java, ND… | 32 | 3566 | maintenance |
| nv-tlabs/PiD PiD is a plug-and-play pixel diffusion decoder from NVIDIA that replaces VAE/RAE decoders, decoding latent representations directly into hi… | 56 | 1045 | active |
| liuyuan-pal/SyncDreamer SyncDreamer is a synchronized multiview diffusion model that generates multiview-consistent images from a single-view image, released with … | 50 | 1045 | active |
| 3DTopia/3DTopia-XL 3DTopia-XL is a 3D diffusion transformer model that generates high-quality 3D assets with PBR materials from a single image or text prompt … | 37 | 1045 | active |
| Tencent-Hunyuan/InstantCharacter InstantCharacter is a tuning-free framework built on diffusion transformers that generates character-consistent images from a single refere… | 29 | 1045 | active |
| scihant/CTPanoramaView A Swift library for iOS that displays spherical (360) or cylindrical panoramas using SceneKit, with touch or motion-based controls. It auto… | 23 | 1045 | stable |
| geotiffjs/geotiff.js geotiff.js is a pure JavaScript library for parsing TIFF and GeoTIFF files, reading geospatial metadata and raw raster data in both browser… | 84 | 1044 | active |
| hku-mars/FAST-Calib FAST-Calib is a C++ tool for fast, target-based extrinsic calibration of LiDAR-camera systems, producing accurate results in about one seco… | 56 | 1044 | active |
| muapi CLI muapi-cli and its Generative Media Skills provide a schema-driven CLI, skill library, and MCP server that let AI agents (Claude Code, Curso… | 93 | 1043 | active |
| aigc3d/LAM LAM is a PyTorch implementation of a Large Avatar Model that reconstructs an animatable 3D Gaussian head from a single image in one forward… | 58 | 1043 | active |
| QianMo/X-PostProcessing-Library X-PostProcessing Library (XPL) is a high-quality open-source post-processing effect library for the Unity engine, built on C# and ShaderLab… | 32 | 3555 | maintenance |
| zenangst/Hue Hue is a Swift utility library for iOS that extends UIColor with convenient color handling features. It provides hex color initialization, … | 23 | 3554 | maintenance |
| Xiaoqi-Zhao-DLUT/MSNet-M2SNet Official PyTorch implementations of MSNet and M2SNet, multi-scale subtraction networks for medical image segmentation such as polyp, lung i… | 74 | 1042 | active |
| mailru/FileAPI FileAPI is a JavaScript library providing tools for working with files in the browser, including multiupload, drag'n'drop, and chunked file… | 32 | 3549 | maintenance |
| iptag/jimeng-api A self-hosted API service that reverse-engineers Jimeng AI (China) and Dreamina (international) to expose free AI image and video generatio… | 10 | 1041 | active |
| foolwood/SiamMask Official PyTorch implementation of SiamMask, a deep learning framework for fast online visual object tracking and video object segmentation… | 35 | 3547 | maintenance |
| Nutlope/blinkshot BlinkShot is an open-source web application that generates AI images in real time as you type, powered by the Flux Schnell model via Togeth… | 67 | 1040 | active |
| GiantappMan/livewallpaper Giantapp Livewallpaper is an open-source wallpaper application for Windows 10/11 that supports both dynamic (video/animated) and static wal… | 74 | 1039 | active |
| lkeab/gaussian-grouping Gaussian Grouping extends 3D Gaussian Splatting to jointly reconstruct and segment open-world 3D scenes by lifting 2D SAM masks into per-Ga… | 27 | 1039 | stable |
| AkimioJR/AutoFilm AutoFilm is a Rust utility that generates .strm files for Emby and Jellyfin media servers, enabling lightweight streaming from network stor… | 88 | 1038 | active |
| Justin62628/Squirrel-RIFE A Chinese-language Windows GUI application for video frame interpolation based on the RIFE algorithm, with NCNN/Vulkan GPU acceleration. It… | 23 | 3526 | maintenance |
| ibireme/YYWebImage YYWebImage is an asynchronous image loading framework for iOS, part of YYKit, offering remote/local image loading, animated WebP/APNG/GIF d… | 23 | 3526 | maintenance |
| kijai/ComfyUI-Hunyuan3DWrapper A ComfyUI custom node wrapper for Tencent's Hunyuan3D-2 model, enabling 3D asset generation from images or text directly inside ComfyUI wor… | 53 | 1035 | active |
| BabitMF/bmf BMF (Babit Multimedia Framework) is a cross-platform, multi-language multimedia and video processing framework developed by ByteDance, offe… | 75 | 1034 | active |
| NVlabs/DiffusionNFT DiffusionNFT is a research library implementing an online reinforcement learning paradigm for diffusion models that optimizes policy direct… | 47 | 1034 | active |
| antimatter15/ocrad.js Ocrad.js is a pure-JavaScript port of the Ocrad OCR engine, compiled to JavaScript via Emscripten, that converts scanned images of text bac… | 32 | 3517 | maintenance |
| ed-asriyan/lottie-converter A C++ command-line tool (also distributed as Docker images) that converts Lottie animations (.json/.lottie) and Telegram animated stickers … | 78 | 1033 | active |
| TTPlanetPig/Comfyui_TTP_Toolset A collection of ComfyUI custom nodes for tiled image processing, including object-aware Smart Tile 2.0 workflows for detail img2img upscali… | 66 | 1033 | active |
| HarborYuan/ovsam Official PyTorch implementation of Open-Vocabulary SAM (ECCV 2024), a model that unifies SAM's interactive segmentation with CLIP's open-vo… | 42 | 1033 | active |
| nodeca/probe-image-size A small JavaScript library that reads image dimensions (width, height, type, mime, orientation) from URLs, streams, or buffers without down… | 76 | 1032 | active |
| podgorskiy/ALAE Official PyTorch implementation of Adversarial Latent Autoencoders (ALAE/StyleALAE), a CVPR 2020 paper combining autoencoders with GAN trai… | 32 | 3511 | maintenance |
| t3mujinpack/t3mujinpack A collection of film emulation presets for the open-source RAW photo developer Darktable, emulating classic films like Fuji Velvia, Kodak P… | 29 | 1031 | active |
| MemeCrafters/meme-generator A Python meme generator library that produces various humorous meme images from user-provided avatars and text using built-in templates. It… | 73 | 1030 | active |
| Jumpat/SegmentAnythingin3D SA3D is a research framework that lifts 2D Segment Anything (SAM) masks into 3D segmentation of objects within a NeRF or 3D Gaussian Splatt… | 40 | 1030 | active |
| zhangyu1818/appicon-forge AppIcon Forge is a web-based app icon generator that lets users customize colors, gradients, borders, shadows, text, and icons (including 2… | 35 | 1030 | active |
| awentzonline/image-analogies A Python library implementing neural image analogies using VGG16 feature maps with PatchMatch-based matching and blending, based on the 'Im… | 23 | 3502 | maintenance |
| continue-revolution/sd-webui-segment-anything A Stable Diffusion WebUI extension that integrates Segment Anything and GroundingDINO to generate segmentation masks from clicks or text pr… | 30 | 3499 | maintenance |
| kuprel/min-dalle min(DALL·E) is a fast, minimal PyTorch port of DALL·E Mini/Mega stripped down for text-to-image inference, with only numpy, requests, pillo… | 31 | 3494 | maintenance |
| DLR-RM/3DObjectTracking A collection of C++ implementations of 3D object tracking algorithms from DLR research, including region-based 6DoF trackers (RBGT, SRT3D, … | 49 | 1027 | active |
| lovasoa/dezoomify-rs dezoomify-rs is a desktop application and CLI tool written in Rust that downloads high-resolution zoomable (tiled) images from websites and… | 100 | 1026 | active |
| zhyever/PatchFusion PatchFusion is a CVPR 2024 end-to-end tile-based framework for high-resolution monocular metric depth estimation from single images. It fus… | 57 | 1026 | active |
| JackAILab/ConsistentID ConsistentID is a diffusion-based portrait generation model and toolkit that preserves facial identity from a single reference image using … | 52 | 1026 | active |
| fudan-zvg/4d-gaussian-splatting Official PyTorch/CUDA implementation of 4D Gaussian Splatting (ICLR 2024), which represents and renders dynamic scenes in real time using 4… | 57 | 1025 | active |
| Any-Distance/any-distance-ios Open source version of Any Distance, an award-winning iOS running and workout tracker app with shareable fitness cards. Released under a cu… | 31 | 1025 | active |
| DingXiaoH/RepVGG RepVGG is a PyTorch implementation of the VGG-style ConvNet architecture from the CVPR 2021 paper, achieving over 84% top-1 ImageNet accura… | 32 | 3478 | maintenance |
| koide3/small_gicp small_gicp is a header-only C++ library with Python bindings for fast, parallelized point cloud registration algorithms including ICP, Poin… | 60 | 1023 | active |
| DBraun/TouchDesigner_Shared A collection of TouchDesigner .tox components and small projects for real-time interactive graphics, including GLSL shaders, geometry, rend… | 40 | 1023 | active |
| BRL-CAD/brlcad BRL-CAD is a cross-platform open source combinatorial solid modeling system with an interactive 3D geometry editor, a high-performance netw… | 87 | 1021 | active |
| manycoretech/aholo-viewer Aholo Viewer is a high-performance TypeScript renderer for 3D Gaussian Splatting (3DGS) scenes and meshes, using a chunked streaming LOD sc… | 79 | 1021 | active |