Browse AI Projects by Category

Image & Vision

Browse AI open-source projects in Image & Vision from the current public snapshot, including licenses, deployment, use cases, limitations, and verified sources.

Comfy-Org/ComfyUI — ComfyUI provides a modular node graph and backend for generative workflows across images, video, audio and 3D. Local model workflows and optional paid API nodes have different dependencies.
AUTOMATIC1111/stable-diffusion-webui — A Gradio-based web interface for running and managing Stable Diffusion image generation on local hardware. It provides text-to-image, image-to-image, inpainting, upscaling, face restoration, and model training capabilit…
linshenkx/prompt-optimizer — This project provides AI prompt optimization, multi-model testing, and evaluation through a web GUI, desktop application, and MCP server. It processes data client-side but requires external AI model provider APIs for in…
huggingface/diffusers — A modular PyTorch library that provides state-of-the-art pretrained diffusion models for image, audio, and video generation. It supplies interchangeable building blocks, noise schedulers, and inference pipelines that de…
opencv/opencv — OpenCV is a free, open-source computer vision library providing a comprehensive set of algorithms for image processing and deep learning. Developers integrate it as a dependency or compile it from source to build comput…
Anil-matcha/Open-Generative-AI — A free, self-hostable generative AI studio that provides access to 200+ models for creating images, video, and audio without built-in content filters. It supports local inference via a bundled engine for desktop users,…
ultralytics/ultralytics — Ultralytics provides YOLO models for real-time computer vision tasks including detection, segmentation, classification, and tracking. It offers a unified CLI and Python API for model training, evaluation, and deployment…
freestylefly/awesome-gpt-image-2 — Provides Prompt-as-Code assets that structure visual instructions into composable components for controllable image-generation workflows. Includes a 520-case gallery, a style-library agent skill, and a website for brows…
basketikun/infinite-canvas — infinite-canvas is an open-source infinite-canvas workbench that combines canvas arrangement, AI image generation, reference-image editing, a chat assistant, a prompt library, and asset management in a single interface…
krillinai/OpenCreator — A Codex-powered creator workspace with visual tools for video, images, voice and reusable creation templates.
ultralytics/yolov5 — YOLOv5 is a PyTorch-based model for vision AI tasks, providing training, inference, and deployment for object detection, instance segmentation, and image classification.
roboflow/supervision — roboflow/supervision is a Python library that provides reusable building blocks to reduce repetitive code in computer vision workflows. Developers can connect classification, detection, or segmentation models and use ut…
ATH-MaaS/Pixelle-Video — Automates the short video creation pipeline from a single text prompt, handling scriptwriting, AI media generation, voiceover synthesis, and final video composition. It is designed for creators who want an automated vid…
ageitgey/face_recognition — A Python library and command-line tool for face detection, facial landmark identification, and face recognition in images, built on dlib's deep learning models. It accepts image files and returns face locations, facial…
deepfakes/faceswap — An open-source application that enables anyone to experiment with deep learning by extracting, training, and swapping faces in images and videos without requiring advanced AI expertise. It supports local execution via C…
invoke-ai/InvokeAI — InvokeAI is a locally hosted creative engine for generating, refining, and iterating on visual media using Stable Diffusion and other generative AI models. It provides a web-based UI, a Unified Canvas for in/out-paintin…
photoprism/photoprism — A self-hostable application for browsing, organizing, and sharing photos and videos. It automatically labels media based on content and recognizes faces to enable search and rediscovery of personal libraries.
ningzimu/codex-ppt-skill — ningzimu/codex-ppt-skill is a Codex skill that converts articles, reports, papers, course notes, and outlines into image-based PowerPoint presentations and assembles them into .pptx files. It also generates speech.md co…
TencentARC/GFPGAN — GFPGAN addresses real-world blind face restoration by leveraging generative priors from a pretrained face GAN. It is a Python library and CLI tool that developers can run locally to restore degraded face images.
helloianneo/ian-xiaohei-illustrations — A Codex skill that analyzes Chinese articles to extract cognitive anchors and generate 16:9 hand-drawn illustrations featuring the 'Xiaohei' IP. It requires OpenAI Codex and an external AI image model to operate.
lllyasviel/ControlNet — controlnet is a neural network structure that adds spatial conditional control to text-to-image diffusion models without destroying the production-ready base model. It copies weights into a locked copy and a trainable c…
BVLC/caffe — Caffe is a deep learning framework built for modular development with an emphasis on speed and expression. It includes reference models, tutorials, and installation guidance for developers and researchers.
ConardLi/garden-skills — garden-skills is a curated collection of production-ready Agent Skills for AI coding agents such as Claude Code, Cursor, and Codex, covering web design, editorial article creation, image generation, web video presentati…
fastai/fastai — fastai provides a layered deep learning library that offers both high-level components for rapid model building and low-level components for custom research approaches. It supports building image classifiers, segmentati…
waooAI/waoowaoo — An AI video-production application that automatically converts novel text into storyboards, characters, scenes, and complete videos. It runs locally via Docker Compose and requires an external AI service API key for inf…
lucidrains/vit-pytorch — vit-pytorch is a PyTorch implementation of the Vision Transformer that performs image classification with a single transformer encoder. It also provides many ViT variants and training wrappers alongside the core model.
junyanz/pytorch-CycleGAN-and-pix2pix — PyTorch implementations of CycleGAN and pix2pix for paired and unpaired image-to-image translation. The repository supports training new models, testing existing ones, and applying pre-trained checkpoints to new dataset…
s1dashu/ip-as-logo-skill — ip-as-logo-skill is an Agent Skill that guides any compatible AI agent to generate extremely simple, cute, company-ready IP mascot images. It constrains generation to roughly 4-7 large shapes with bold rounded silhouett…
NVlabs/Sana — Sana is an open-source training and inference framework for high-resolution image and video generation. It uses Linear Attention in DiT to reduce computational cost and latency, enabling deployment on laptop GPUs with l…
spmallick/learnopencv — An educational repository of C++ and Python code examples for computer vision, deep learning, and AI concepts. The implementations are tightly coupled with accompanying blog posts and are intended as learning materials…

Search

Browse AI Projects by Category