Project Overview

An AI-powered image editing platform designed for designers, marketing professionals, and content creators. It leverages Tongyi Qwen’s image generation and editing models to enable intuitive image creation and modification directly in the browser—no need to manage underlying models or API keys.

Problems Solved

• High barrier to entry: Using image models directly requires handling API keys, parameters, and endpoints manually.
• Creative teams need rapid prompt iteration and side-by-side result comparison—but lack a unified, collaborative interface.
• Commercial assets often require adaptation or repurposing, yet professional design tools carry steep learning curves.

Use Cases

• Marketing Assets: Instantly transform product photos into on-brand promotional visuals across multiple styles.
• Content Creation: Generate batch-ready illustrations for WeChat Official Accounts, Xiaohongshu (Little Red Book), or short videos.
• Design Drafting: Use AI to produce initial mockups for refinement—accelerating design handoff and iteration cycles.
• Prompt Engineering: Fine-tune prompts and negative prompts, then instantly compare multiple output variants.

Key Features

• Supports both image uploads and URL inputs—zero setup required.
• Dual control via prompt + negative prompt for precise stylistic and compositional adjustments.
• Generate multiple variations simultaneously, at customizable resolutions.
• Results open in new tabs—ideal for quick visual comparison and one-click saving.

Tech Stack

Next.js + Tongyi Qwen Image Models.