Ecommerce Main Image Generation
Paste the following prompt into your AI chat to install this skill:
Please install @user_db7424f5/udb7-ecommerce-main-image into your AI assistant according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
E-commerce main images usually need a clear product subject, clean background, no text or watermark, and a layout that can be used directly. Generic text-to-image calls often produce unstable product size, busy backgrounds, extra text, or weak reference-image control. This skill frames the task as requirement parsing, prompt construction, multi-backend generation, and fallback.
How It Works
It extracts product type, style, color features, and scene usage from the description, then builds a more controlled English prompt with constraints such as centered product shot, clean white background, and no text. It then tries configured backends in order: Gemini API, Jimeng, or Stability AI. If a reference image is a URL, it first downloads it to base64. It generates 3 candidate images, retries with the next backend on failure, and applies a 120-second timeout. Output prefers image URLs, falling back to base64.
Boundaries
This is useful for quickly producing white or solid-background main images, especially for 3C products, apparel, and cosmetics. It requires at least one image generation backend key, and Jimeng needs a local service. It focuses on composition and main-image style constraints, not real photography, complex layout, or full brand identity design.
Use Cases
- Create white or light-background main images for summer women's apparel, emphasizing light green florals and a fresh style.
- Generate three candidate main images showing a 3C product from the front or 45-degree angle while keeping the background uncluttered.
- Use an existing reference-image URL to generate main images that preserve product features, with automatic fallback to available APIs.
- Prepare watermark-free, text-free, solid-background hero images for cosmetics detail pages, ready for later layout work.
Best For
- E-commerce designers handling listing images: need quick candidate hero images following white-background and 60-80% product-size rules.
- Operations staff processing many SKUs: need to turn product, color, and style descriptions into usable listing image assets.
- Frontend or full-stack engineers integrating image APIs: need to call Gemini, Jimeng, or Stability AI with failure fallback.
- Visual leads building independent product pages: need watermark-free, text-free solid-background images for later layout.
Related Skills
A ComfyUI image-generation skill that uses a five-step dialog to collect prompts, prefill templates, confirm parameters, submit API jobs, and return results.
A design-system guidance skill for Impeccable that produces token-based rules, component states, accessibility criteria, and QA checklists.
Director-level video lapian that diagnoses material precision, then produces frame evidence, director analysis, a style bible, and a showcase video.
Plan and brief Amazon MAIN, Listing, and A+ image sets from verified product facts, then return plan and image QA status.