Trending Computer vision repos

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

Fast CPU OCR: line detection, CTC recognition, reading order, markdown

Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.

Method-agnostic smart garden companion built with React Native, Expo, and TypeScript. Adapts to soil, hydro, container, or indoor setups with location-aware intelligence, OpenWeather integration, and privacy-first, on-device Gemini AI plant diagnostics.

Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.

Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

AI-assisted RAW photo developer: GPT vision advisor proposes an EditRecipe, a deterministic Rust engine renders it — Lightroom-compatible XMP sidecars, 24 RAW formats + baked images, measured (not guessed) Lightroom mask geometry, local GUI/web UI, AI denoise & segmentation sidecars

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.

把 Codex imagegen 的工作流与提示词库带到任意智能体；支持 npm/pnpm 一键安装、配套 skill、独立 API 与 Qwen-Image 兼容网关。

Real-time generative rendering for interactive worlds, from any visual reference.

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.

Edit photos by describing the change, on your own GPU. One installer, no Python, no cloud. Qwen-Image 2.1 for Windows and Mac, with an MCP server for AI agents.

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

A Unified Large-Scale Benchmark for World Generation toward World Intelligence

Manga / black & white comic filter for ComfyUI: crisp lines, flat tones, real screentone (halftone), solid blacks and panel frames.

Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)

Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras.

Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.

自然言語で頼むと漫画の原稿が出てくる Claude Code スキル — OMNY(ネームYAML)設計→作画→回収→検品→納品のパイプライン