Image, video & design

Computer vision

Computer vision projects read images and video rather than generate them, answering questions about what a picture shows, spotting objects, or working out where a photo was taken. LLaVA and Ask-Anything show the pattern: a vision model paired with a language model so the agent can describe scenes and hold a conversation about them.

430 agents · most starred first

Top 100 of 430

LLaVA★ 25,084

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

geo-sleuth★ 7,325

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.

snow-shot★ 4,886

超好用的截图工具

Ask-Anything★ 3,361

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

InternGPT★ 3,202

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)

DeepCamera★ 3,143

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.

VideoPipe★ 2,994

A cross-platform video structuring (video analysis) framework based on CV models & mLLM.

cambrian★ 2,010

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

video-search-and-summarization★ 2,002

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

awesome-openai-vision-api-experiments★ 1,701

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API 🔥

Video-ChatGPT★ 1,516

[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.

dsh-vision-router★ 1,291

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

agent-vision-toolkit★ 1,266

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

groundingLMM★ 969

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

MM-REACT★ 965

Official repo for MM-REACT

4KAgent★ 842

[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!

ghostwriter★ 573

Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!

2txt★ 554

Image to text, fast.

PicQuery★ 529

🔍 Search local images with natural language on Android, powered by OpenAI's CLIP model. / 在 Android 上用自然语言搜索本地图片 (基于 OpenAI 的 CLIP 模型)

DOVideo-AI★ 497

一个面向长视频内容理解的 Video Agent 平台。

clifs★ 483

Contrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP

Olympus★ 428

[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"

OPERA★ 416

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

Qwen-VL-Chat★ 391

transformers pytorch qwen text-generation custom_code zh

VideoMind★ 365

🧠 VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning (ICLR 2026)

snip★ 352

The visual communication layer between humans and AI agents. Capture, annotate, render diagrams, and organize with AI — powered by Electron and Ollama. macOS & Linux.

ViP-LLaVA★ 338

[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

chat-with-nerf★ 322

[ICRA 2024] Chat with NeRF enables users to interact with a NeRF model by typing in natural language.

VideoAgent★ 319

This is the official code of VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding (ECCV 2024)

VideoGPT-plus★ 294

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

WebcamGPT-Vision★ 291

Lightweight GPT-4 Vision processing over the Webcam

CLIP-ImageSearch-NCNN★ 281

CLIP⚡NCNN⚡基于自然语言的图片搜索(Image Search)⚡以字搜图⚡x86⚡Android

LongVT★ 274

[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

LLaVAR★ 269

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

BLIVA★ 260

(AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions

dolphin★ 257

General video interaction platform based on LLMs, including Video ChatGPT

voxelgpt★ 255

AI assistant that can query visual datasets, search the FiftyOne docs, and answer general computer vision questions

agenticSTAR★ 240

AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos

OmniFusion★ 234

OmniFusion — a multimodal model to communicate using text and images

cdaf★ 226

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skill, reproducible benchmark.

cogvlm2-llama3-chat-19B★ 220

transformers safetensors text-generation chat cogvlm2 conversational

openai-captcha-detection★ 211

openai-captcha-detection 是一个使用 OpenAI 进行验证码识别的工具。目前验证码识别准确率100%,通过调用 OpenAI 的 API,这个项目可以实现对复杂验证码图片的文本识别,帮助开发者在验证码处理场景中进行自动化操作。openai-captcha-detection is a tool that uses OpenAI for captcha recognition. Currently, it achieves a 100% accuracy rate in captcha recognition.

Agent4FaceForgery★ 208

Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery

clip-image-sorter★ 201

Sort a folder of images according to their similarity with provided text in your browser (uses a browser-ported version of OpenAI's CLIP model and the web's new File System Access API)

cogvlm-chat-hf★ 200

transformers safetensors text-generation custom_code en arxiv:2311.03079

CVPR2018_attention★ 180

Context Encoding for Semantic Segmentation MegaDepth: Learning Single-View Depth Prediction from Internet Photos LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume On the Robustness of Semantic Segmentation Models to Adversarial Attacks SPLATNet: Sparse Lattice Networks for Point Cloud Processing Left-Right Comparative Recurrent Model for Stereo Matching Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior Unsupervised CCA Discovering Point Lights with Intensity Distance Fields CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation Learning a Discriminative Feature Network for Semantic Segmentation Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation Unsupervised Deep Generative Adversarial Hashing Network Monocular Relative Depth Perception with Web Stereo Data Supervision Single Image Reflection Separation with Perceptual Losses Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds Decorrelated Batch Normalization Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints PU-Net: Point Cloud Upsampling Network Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer Tell Me Where To Look: Guided Attention Inference Network Residual Dense Network for Image Super-Resolution Reflection Removal for Large-Scale 3D Point Clouds PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image Fully Convolutional Adaptation Networks for Semantic Segmentation CRRN: Multi-Scale Guided Concurrent Reflection Removal Network DenseASPP: Densely Connected Networks for Semantic Segmentation

clip_playground★ 175

An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities

cerul★ 166

Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

PyVision★ 165

[MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."

AgentThink★ 154

[EMNLP2025]Official implementation: Agent-style vision question answer in Autonomous Driving!

YoloWebAgentStarter★ 154

Local-first YOLO workbench for annotation, training, evaluation, and AI assistance.

PALI3★ 146

Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"

sam3-segmentation★ 145

Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.

amblegpt★ 141

Video surveilance footage analyst powered by GPT

MiniGPT-3D★ 132

[MM 2024] [Need only a 3090] MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

fashion-assistant★ 120

Our idea is to combine the power of computer vision model and LLMs. We use YOLO, CLIP and DINOv2 to extract high-level features from images. We pass the prompt, along with the extracted features, to LLM, allowing for advanced image dataset queries.

EventGPT★ 115

🔥[CVPR2025] EventGPT: Event Stream Understanding with Multimodal Large Language Models

Modality-Integration-Rate★ 114

[ICCV 2025] The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

gpt4-vision-chrome-extension★ 108

GPT-4 Vision Chrome Extension

MP5★ 108

[CVPR2024] This is the official implement of MP5

VideoGLaMM★ 106

[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

detect-skill★ 105

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

SEEChat★ 102

Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM

Qwen-VL-Chat-Int4★ 102

transformers safetensors qwen text-generation custom_code zh

vggt-mps★ 93

VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

Promsa★ 93

[ECCV 2026] Promsa: Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering

VideoHub★ 93

一个面向长视频内容理解的 Video Agent 平台。

supergemma4-26b-abliterated-multimodal★ 91

transformers safetensors gemma4 image-text-to-text bf16 multimodal

ai-visualizer★ 91

Give your AI agent a face. Four full-screen visualizers. A living circuit board with a cinematic fly-through, a particle-orb starburst, Matrix rain that looks back, and a constellation brain. All driven live by your voice agent's signal bus. Zero dependencies: a browser and one tiny Python server. Pairs with backtalk out of the box.

OmniAgent★ 90

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

SoccerAgent★ 89

[ACM Multimedia 2025] "Multi-Agent System for Comprehensive Soccer Understanding"

Arion★ 86

Arion is the first agentic AI desktop app for geospatial analysis, developed by GeoRetina Inc.

MMCTAgent★ 84

Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning

mlx_clip★ 81

A simple package to use CLIP on apple silicon using the MLX libraries from Apple

GPT4-Vision-React-Starter★ 77

Early Alpha Release: Chat with Your Image - Leveraging GPT-4 Vision and Function Calls for AI-Powered Image Analysis and Description

FreeVA★ 70

FreeVA: Offline MLLM as Training-Free Video Assistant

cogagent-chat-hf★ 69

transformers safetensors text-generation custom_code en arxiv:2312.08914

vailabel-studio★ 68

Vailabel Studio - a local-first desktop studio that labels your data with an offline AI copilot. Private by default. Windows, macOS, Linux.

CShade★ 63

Image and video processing shaders for ReShade.

RailMind-AI★ 62

Agentic AI platform transforming passive CCTV into proactive railway safety intelligence. Real-time behavioural detection (suicide risk, pickpocketing) via YOLOv8 + BiLSTM + multi-agent reasoning — zero new hardware, privacy-first, no facial recognition.

openai-vision-api-for-videos★ 61

Extract information, summarize, ask questions, and search videos using OpenAI's Vision API 🚀🎦

CLIP-tf2★ 55

OpenAI CLIP converted to Tensorflow 2/Keras

AutoLabel-Forge★ 55

SmartLabel AI 2026: Auto-Annotate Any Object via LLM-Powered Prompt Parsing

llama-multimodal-vqa★ 54

Multimodal Instruction Tuning for Llama 3

SkeletonAgent★ 54

PyTorch implementation of "SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition"

AI-Photographer-Agent-ROCm★ 54

Private local AI Photographer Agent on AMD Radeon and ROCm

ReAgent-V★ 51

[NeurIPS'25] ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

CLIP-android-demo★ 50

A demo for running quantized CLIP model (ViT-B/32) on Android.

VideoAgentTrek★ 50

The official repo of VideoAgentTrek

AgentDVR-Plugins★ 50

Plugins for Agent DVR

video-analyzer★ 50

Analyze any video and produce an .avt (Agentic Video Transcript) file — structured visual descriptions, timestamped transcripts, scene tags, and frame references for AI agent consumption.

computer-vision-skills★ 50

Agent-ready Skills for Roboflow and Computer Vision workflows

Video-RSI★ 49

[Arxiv] Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution

IR3D-Bench★ 48

[NeurIPS DB 2025] IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

egagent★ 48

Code for "Agentic Very Long Video Understanding" (EGAgent) [ACL 2026 Main]

Light-Omni★ 47

[IEEE TMM] Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory

llava-llama-2-13b-chat-lightning-preview★ 47

transformers pytorch llava text-generation region:us

HPT1_5-Air-Llama-3-8B-Instruct-multimodal★ 46

transformers safetensors llama text-generation multimodal vision-language

VisioNomicon★ 45

A utility that leverages GPT-4o to rename image files based on their content

DOtAv2★ 43

Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels. (CVPR2025)

More in Image, video & design