Image, video & design

Computer vision

430 agents · most starred first

Computer vision, page 2 of 5

Halligan★ 43

Are CAPTCHAs Still Bot-hard? Generalized Visual CAPTCHA Solving with Agentic Vision Language Model

LVAgent★ 42

Code of LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

Refer-Agent★ 42

[CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

CopilotJ★ 42

CopilotJ: A Conversational Multi-agent System for Intelligent and Efficient Bioimage Analysis

liquid-quality-agent★ 41

工业液位与字符检测质量 Agent:集成 YOLO、液位反演、字符识别、受控复检、确定性仲裁、RAG 解释与 SQLite 审计。

timeleapcam★ 40

Time Leap Cam - Super Long Term Time-Lapse Camera and Monitoring by OpenAI

Smart-Traffic-Monitoring-System★ 40

An intelligent traffic monitoring system that collects traffic flow and metrics including average speed and vehicle counts for each road. Features real-time data visualization with interactive dashboards and an integrated AI Agent chatbot for querying processed traffic data in real-time.

atlas★ 39

Solving Computer Vision with AI agents

VideoMultiAgents★ 39

VideoMultiAgents: A Multi-Agent Framework for Video Question Answering

gpt-4v-distribution-shift★ 38

Code for ICLR'24 workshop ME-FoMo-How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation

LightUp★ 38

AI Genius annotations for every page on the web.

ZYC.TilePyramid.Agent★ 37

A WPF workspace for large images and whole-slide images, with layered annotations, MCP agent integration, and human-in-the-loop review.

reelql★ 36

Give your agent eyes: any video link in, one typed JSON out. A Claude skill + API.

ballradar★ 35

[KDD 2023] Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTM

EdiVal★ 35

[ICLR 2026] Official code for [EdiVal-Agent Automated, object-centric evaluation for multi-turn instruction-based image editing]

tools★ 34

Free AI-powered Image Takedown Tool

VideoHV-Agent★ 33

Official implementation of "Think, Then Verify: A Hypothesis–Verification Multi-Agent Framework for Long Video Understanding(CVPR'2026)"

MR-Video★ 32

MR. Video: MapReduce is the Principle for Long Video Understanding

gpt4-image-api★ 31

Small tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature. Very quickly made, you should not rely on this on prod.

TAB-Agent★ 31

[EMNLP 2026 Main] Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding

Plants-Identification★ 30

🌻 Deep learning project of Taiwan plants classification and detection with chatbot implementation

ComfyUI-Segmentation-Agent★ 29

LLM-based character segmentation agent for ComfyUI based on SAM 3 and the SAM 3 Agent notebook

Emu2-Chat★ 29

transformers pytorch text-generation custom_code en arxiv:2312.13286

video-expert-analyzer-vnext★ 28

Long-task-oriented video analysis skill for Claude Code (/vea) — resumable staged execution, automatic parallel scoring, OpenClaw orchestration, audiovisual analysis with agent handoff

NoteMR★ 27

[CVPR 2025] Code for "Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering".

camroll★ 27

camroll • an AI assistant for your personal camera roll 🎞️ • Personal VQA

pyscreen★ 26

PyScreen is an AI-powered tool that extracts, analyzes, and visualizes data from screen recordings. It leverages advanced computer vision, text processing, and AI techniques to provide valuable insights such as dominant color schemes, frequently used words, and content descriptions using OpenAI's GPT-4 model.

Video_Dariy★ 25

这是一个面向家庭场景的离线监控视频分析系统。项目以 NAS/目录中的摄像头录像为输入,自动完成视频扫描、会话合并、AI 事件识别、家庭日报生成,并提供 Web 管理后台、自然语言问答、Webhook 与 MCP 对外能力。

chatgpt-with-image-sample★ 24

This sample project integrates OpenAI's GPT-4 Vision, with advanced image recognition capabilities, and DALL·E 3, the state-of-the-art image generation model, with the Chat completions API. This powerful combination allows for simultaneous image creation and analysis.

hybrid-image-tagger★ 24

🚀 A powerful tool to automatically generate descriptive tags for image datasets using both WD Tagger and VLM, with a user-friendly web UI. Perfect for preparing training data for Stable Diffusion and LoRA.

Described★ 23

Automatically describe images sent by users on popular media platforms, incredibly useful for the visually impaired and for complicated imagery.

gpt4v-screenshot-analyzer★ 23

This tool offers an interactive way to analyze and understand your screenshots using OpenAI's GPT-4 Vision API. Capture any part of your screen and engage in a dialogue with ChatGPT to uncover detailed insights, ask follow-up questions, and explore visual data in a user-friendly format.

Multi-Agent-VQA★ 23

[CVPR 2024 CVinW] Multi-Agent VQA: Exploring Multi-Agent Foundation Models on Zero-Shot Visual Question Answering

ClawGallery★ 23

Agent-native screenshot gallery CLI: index, caption, search & safely rename local photos.

rename-screenshot★ 22

Rename Mac screenshots based on its contents with local Ollama or ChatGPT

seeit-ai★ 22

面向长视频理解与证据分析的 Video Agent 平台,基于 FastAPI、Vue、MySQL、Redis 和 RocketMQ,支持 ASR/OCR 时间轴证据。

yolo-v11-pose-lab★ 21

gradio mcp-server-track ultralytics yolo image processing human pose mcp-server region:us

edgesentinel-visionops★ 21

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

AOAI-GPT4Vision-Streamlit-SDKv1★ 20

Using Azure OpenAI deployment of GPT-4 Turbo with Vision to analyse out-of-stock situation in a fictitious retail shop.

ai-screen-analyzer★ 20

AI Screen Analyzer allows users to capture screenshots, analyze them using various AI providers and models, and engage in conversations about the images.

Dendro-Inspector★ 20

Eval-driven multimodal agent for identifying trees, logs, bark, leaves and wood from photographs. Dendrology is the reference domain; the engineering subject is evidence handling, calibrated uncertainty and evaluation.

LLava-Image-Analyzer★ 19

Llava, Ollama and Streamlit | Create POWERFUL Image Analyzer Chatbot for FREE - Windows & Mac

ai-vision-dataset-builder★ 19

Generating diverse and realistic datasets for computer vision training using AI.

image-search★ 18

Simple Image Search powered by Multimodal Foundation Models (OpenAI Clip and Microsoft GLIP)

object-detection-openai★ 18

Object detection using Open AI Vision Model

gpt-4v-demos★ 18

🤖 GPT-4V Demos • Test the model's vision capabilities in your browser using Streamlit • Easy setup

Monkey-Chat★ 18

transformers pytorch monkey text-generation custom_code arxiv:2311.06607

Clip-Image-Search★ 17

Semantic Text-Image/Image-Text/Image-Image Search Engine using CLIP

GPT-4-Vision-Architecture-Scanner★ 17

A web-based tool that utilizes GPT-4's vision capabilities to analyze and describe system architecture diagrams, providing instant insights and detailed breakdowns in an interactive chat interface.

Image-AltText-Generator★ 17

Generate an alt-text description for an image using ollama and llama3.2-vision

stolen-bike-watch★ 17

Finds a stolen bike on second-hand marketplaces by ranking photos, not keywords — a CLIP pre-gate in front of a vision-LLM recognition pass. ~900 listings/day → ~4 worth looking at, $14/mo.

GPT-4-Vision-for-HoloLens★ 16

Capture images with HoloLens and receive descriptive responses from OpenAI's GPT-4V(ision).

ai-video-analyzer★ 16

AI Video Analyzer & Chat Agent is a robust AI application built with Streamlit, Agno, & Langchain's DuckDuckGo Tool. Integrating Gemini 1.5 Flash, it enables video analysis, insight extraction, and AI-powered chat with features like content analysis, real-time web searches, and multi-modal analysis for research, education, and interactive learning.

Captioner★ 16

gradio region:us

Video-ChatGPT★ 16

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

image-to-text-to-speech★ 15

An app that uses Hugging Face AI models together with OpenAI & LangChain, to generate text from an image, which then generates audio from the text

visualdialog-pytorch★ 15

Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359

PyVision★ 15

gradio region:us

MIST★ 15

Execution Before Memory: diagnosing memory failures in video world models.

InSight-o3★ 14

[ICLR'26] InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search

Gemini_Pro_Chatbot_with_Image_Caption_Generation★ 14

streamlit region:us

Art-Historian-AI★ 13

gradio agent-demo-track region:us

Pixtral-Multimodal-Chatbot★ 13

gradio region:us

img2rag★ 12

Convert any image into a Region Adjacency Graph (RAG)

image-analysis-router★ 12

智能选择 17 套分析方案的图像分析分流 Skill:先判断该怎么读图,再输出定向分析和学习建议。

LLM-Image-To-Description★ 11

streamlit region:us

Image-Forgery-Detection★ 10

A deep convolutional neural network for the detection as well as localization of the area of manipulation in forged images, bearing forgeries of simple as well as complex nature. Further along, the trained model is interfaced with a web application for users to interact with the model in a simple and effective manner, and finally, we also develop a chatbot for further easing the process of interaction with the model and effectively tackling the problem of fake news forwards in popular internet messaging platforms such as WhatsApp.

CoI★ 10

Chain of Images for Intuitively Reasoning

Image-Caption-Generation-using-LLMs-GEMINI-★ 10

we generate captions to the images which are given by user(user input) using prompt engineering and Generative AI

awesome-clip-projects★ 10

A list of projects that use OpenAI's CLIP model.

Solar-AI-Rooftop★ 10

An AI-powered tool that detects rooftops from satellite images, estimates solar panel potential and ROI, and provides smart recommendations using GPT

paligemma-waveui★ 10

gradio region:us

ChatTS-8B★ 10

transformers pytorch qwen3ts feature-extraction text-generation conversational

image-analysis-mcp★ 10

Image analysis and visual understanding tools for AI agents — describe, detect, extract from any image.

multimodal-traffic-inference★ 10

A stateful vision-language workflow that validates crowdsourced traffic evidence, extracts vehicle identifiers, and maps violations to statutory penalties

Artificial-Intelligence-Supported-Video-Forensic-Investigation★ 9

This project provides evidence for AI-Assisted Video Forensics

cog-batch-image-captioning★ 9

Caption images for lora training

gpt4-vision-plugin★ 9

Chat with your images using GPT-4 Vision!

Customer-emotion-recognition★ 9

Customer emotion recognition is technology that helps businesses automatically understand customer feelings.

perceptual-copilot★ 9

gradio region:us

vision-primitives-mcp★ 9

Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-file Python, Pillow-only dependency.

Track-Explorer★ 8

LLM-Powered Agents for Object Tracking Databases

Talk2FastVLM★ 8

Flask app to interact with FastVLM using CPU only

StrangerX-Multimodal-ChatBot★ 8

Multimodal-ChatBot-App, LLM Model Id Doesn't work outside, since it is opeartable inside the Huggingface Models. Recommended to Deploy inside Huggingface Spaces SDK as StreamLit.

Image-Denoiser★ 8

Image Denoising and Classification using Machine Learning . Can detect saltpepper/speckle/gaussian/Rayleigh/uniform/exponential noises , and apply the best filter to denoise the image . Canny Edge Detection is also a feature along with creating images using prompts through OpenAi "DALLE" API ... backend (python)

AI-Video-Analysis★ 8

Upload a Video and get conversational responses about its content

webcam_chat_with_aoai_gpt4o★ 8

Discover the GPT-4o multimodal model at Microsoft Build 2024, now with text and image capabilities. My prototype enhances chats with real-time camera snapshots, powered by Flask, OpenCV, and Azure’s OpenAI Services. It’s interactive, visual, and simple to use. Give it a try!

multiclass-image-classification-using-multimodal-llms★ 8

A comprehensive comparison of multimodal models - llama3.2-vision, minicpm-v, llava-llama3, llava, llava13:b and closed source models for animal classification tasks. This project evaluates various models' performance in classifying 10 different animal species, ranging from common to rare animals.

mood-scroll★ 8

Chrome extension that classifies your TikTok feed by mood with GPT-4o vision — auto-likes matches, skips the rest, retrains your For You page.

Phi-3.5-Chatbot-Vision-App★ 8

gradio region:us

InternVL-Chat-ViT-6B-Vicuna-7B★ 8

transformers pytorch tensorboard llava text-generation visual-question-answering

photo_agent★ 8

你的私人摄影指导团队

D2R-AI-Item-Tracker★ 8

AI-powered OCR for Diablo II: Resurrected - batch-extract item tooltips from screenshots using Vision LLMs (OpenAI, Groq, OpenRouter, LM Studio/Ollama). No Tesseract or EasyOCR needed.

genpark-lens★ 8

An open-source Visual Agent that turns any image into a structured curiosity engine across 4 dimensions.

genpark-auto-annotator★ 8

Zero-shot computer vision dataset labeler.

hias-tassai-facial-recognition★ 7

HIAS TassAI Facial Recognition Agent processes streams from local or remote cameras to identify known and unknown humans.

ScalpSmart★ 7
RizzGlasses★ 7

Rizz glasses (CarletonU Hackathon)

vision-agent-with-llava★ 7

static region:us

Medical-Image-Classification★ 7

gradio region:us

More in Image, video & design