ai-picture-editor
2026 年编程导航 AI 编程实战新项目,基于 React 19 + FastAPI + LangChain + LangGraph + Konva 的 AI 修图智能体,支持自然语言驱动修图、21 种编辑工具、文生图、智能抠
What is ai-picture-editor?
2026 年编程导航 AI 编程实战新项目,基于 React 19 + FastAPI + LangChain + LangGraph + Konva 的 AI 修图智能体,支持自然语言驱动修图、21 种编辑工具、文生图、智能抠图、图层拆分、区域编辑、多步计划。覆盖 AI Agent 架构、SSE 实时推送、异步任务队列、Canvas 画布引擎。用一套教程掌握 AI Agent 全栈开发,不到一周学完,给你的简历增加竞争力
Overview of ai-picture-editor
What it is
ai-picture-editor is a full-stack AI image editing project that uses an AI Agent to drive image editing. It is built with Python 3.13, FastAPI, LangChain, LangGraph, React 19, and Konva. The project is designed as a teaching resource, providing a complete tutorial, resume guidance, interview questions, and Q&A support. It covers AI Agent architecture, SSE real-time push, asynchronous task queues, and a Canvas drawing engine.
Key features
- AI text-to-image generation with four candidate images displayed in a grid, with progress pushed via SSE.
- A professional canvas editor built with react-konva, supporting zoom, pan, layer management, undo/redo, and a before/after comparison slider.
- Natural language-driven image editing: users input a sentence, and the AI Agent plans and executes editing steps automatically.
- 21 editing tools, including background removal, color adjustment (11 parameters), crop, flip, scale, rotate, move, AI background replacement, AI outpainting, and super-resolution.
- Smart region selection using SAM (Segment Anything Model) with point-click and brush modes.
- Local editing: inpainting for object removal and prompt-based local replacement.
- Layer splitting: separate images into subject, background, and OCR text layers, with independent operations and JSONB persistence.
- Multi-step planning with server-side validation, topological sorting, and human-in-the-loop confirmation.
Use cases
- Learning AI Agent development and full-stack AI application building.
- Building a professional-grade AI image editing tool with natural language interaction.
- Demonstrating skills in Python backend, React frontend, and AI integration for job applications.
Getting started
See the repository README for detailed instructions. The quick start involves: bash git clone https://github.com/yuyuanweb/ai-retouch-agent.git cd ai-retouch-agent docker compose up -d cd backend uv sync --all-extras cp .env.example .env uv run alembic upgrade head uv run uvicorn app.main:app --reload --host 0.0.0.0 --port 7302 uv run arq app.worker.WorkerSettings cd frontend npm install npm run dev
License and pricing
The license is not stated in the provided metadata. The project is listed as open source, but no specific license is mentioned. Pricing is not applicable as it is an open-source project.
Based on the project's public README and repository metadata.