FlowCay logo
FlowCay
Ecom Details Image UI

Ecom Details Image UI

Web Agent version of ecom-details-image Skill: describe a product in Chinese and generate professional e-commerce images with scene/pose/style controls.

58

Install command

npx skills add https://github.com/liangdabiao/ecom-details-image-ui
SkillOpen SourceAll Platforms
Added on Popularity 9

Details

Overview

Ecom Details Image UI (EcomImageChat) is the web-agent version of the ecom-details-image Skill. Describe your product in Chinese and get a professional e-commerce image in about 30 seconds. Upload a reference photo to transform the scene, pose or style while preserving the product itself. It runs as an open-source app on Tencent Cloud EdgeOne Makers.

Key Features

  • Text-to-image: describe your product and needs in natural language, AI writes the prompt and generates the image directly.
  • Image-to-image (reference photo): upload a product photo (PNG/JPG/WEBP, up to 8MB); AI analyzes it and preserves color, material and design while changing scene/pose/light/style.
  • 25 e-commerce scene templates: white-background hero, lifestyle, detail macro, social media, UGC, model shots, infographics, exploded views, packaging and more.
  • GPT-Image-2 ruleset: hex color codes, numeric ratios, explicit whitespace, negative lists and 3-layer information architecture baked into prompts.
  • Conversion-driven diagnosis: auto-detects visual-driven, pain-point-driven or emotional-value-driven products.
  • Campaign Style Lock: locks palette, light, font, background and composition across multi-image sets.
  • Real-time SSE progress: upload, recognition, submission, download and storage streamed to the frontend.

How to Use

  1. Use a Skill-compatible agent such as Claude Code, Cursor, or Codex.
  2. Install from the terminal (Node.js required):
npx skills add https://github.com/liangdabiao/ecom-details-image-ui

Or paste the install prompt from this tool page into your agent and ask it to install for you. 3. Restart / reload the agent so the new Skill is loaded. 4. Invoke the Skill with its slash commands or by asking the agent to run the workflow described in Overview / Key Features. 5. Review outputs before publishing — treat model-generated copy, images, and data as drafts.

Pricing

Open-source project. The EdgeOne Makers server, DeepSeek chat model and Agnes AI image/vision APIs are free to use; you may bring your own API keys via environment variables if desired.

Integrations

  • Tencent Cloud EdgeOne Makers (Agent Node Runtime + Cloud Functions + Blob Storage)
  • Claude Agent SDK
  • DeepSeek (main chat model, Anthropic-compatible via EdgeOne AI Gateway)
  • Agnes-2.0-Flash (image recognition) and Agnes Image 2.1 Flash (generation)
  • Frontend: React 18 + Tailwind CSS v4 + Vite 6

Best For

Cross-border and domestic e-commerce sellers who want a free, browser-based AI image studio with Chinese-language workflow and scene/pose/style controls.

FAQ

What is EcomImageChat?

The web-agent version of the ecom-details-image Skill — a browser app that generates e-commerce images from a Chinese description, optionally from a reference photo.

Is it free?

Yes — the app, server runtime, chat model and Agnes image APIs are free. You can optionally configure your own API keys.

Does uploading a reference image work?

Yes — uploading any reference forces image-to-image mode, preserving the product's color/material/pattern while changing the scene.

What are the current limits?

One image per conversation due to a 120-second cloud-function limit; multi-image PDP sets are a future enhancement.