# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Architecture Overview

This is a Hugging Face Spaces application that provides image editing capabilities using the Qwen-Image-Edit model. The application consists of a single Gradio interface (`app.py`) that orchestrates:

1. **Image Processing Pipeline**: Uses `QwenImageEditPipeline` from diffusers for the core image editing functionality
2. **Prompt Enhancement**: Integrates with DashScope API (`qwen-vl-max-latest`) to automatically rewrite and enhance user edit instructions using a detailed system prompt
3. **Gradio Interface**: Web UI with image upload, text input, and advanced parameter controls

## Key Components

- **Main Pipeline**: `QwenImageEditPipeline` loaded from "Qwen/Qwen-Image-Edit" model
- **Prompt Polishing**: `polish_prompt()` function that uses DashScope API to enhance user instructions via a comprehensive system prompt template
- **Inference Function**: `infer()` decorated with `@spaces.GPU(duration=120)` for GPU acceleration
- **UI Layout**: Single-page Gradio interface with examples and advanced settings accordion

## Environment Requirements

- **GPU**: CUDA-enabled environment preferred (falls back to CPU)
- **API Key**: `DASH_API_KEY` environment variable required for prompt enhancement via DashScope
- **Dependencies**: PyTorch, diffusers (git version), transformers, dashscope, gradio

## Development Commands

Install dependencies:
```bash
pip install -r requirements.txt
```

Run the application:
```bash
python app.py
```

## Configuration Notes

- Default inference settings: 50 steps, guidance scale 4.0, bfloat16 dtype
- Hardcoded negative prompt: single space character
- GPU duration limit: 120 seconds for Spaces environment
- Examples include three preset image/prompt combinations for testing