Pagewright is an LLM-orchestrated tool that generates pixel-accurate e-commerce detail-page long images by extracting structured data from product URLs or user uploads and rendering deterministic HTML to PNG, avoiding the text fidelity issues of text-to-image models.

Stars

10

7-day growth

No data

Forks

0

Open issues

0

License

NOASSERTION

Last updated

2026-06-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It solves the critical problem of data fidelity in AI-generated e-commerce images by having the LLM only handle structuring, writing, and translation while a deterministic engine renders exact text, numbers, and real assets, making it auditable, reproducible, and editable.

Who it is for

  • E-commerce sellers and marketers
  • Developers building product page automation
  • Non-technical users needing quick detail-page generation
  • Online retailers on Taobao, Tmall, Amazon, Shopify

Use cases

  • Generating bilingual (Chinese-English) product detail-page images from a URL or manual uploads
  • Automating the creation of consistent, data-accurate long images for multiple products
  • Editing a single field and instantly re-rendering the entire detail page without model costs
  • Auditing and verifying that every number and asset on the page traces back to the original source data

Strengths

  • Deterministic rendering ensures exact prices, specs, and text without garbled characters or hallucinated logos
  • Local-first design keeps uploads and rendering on the user's machine, only LLM calls leave the device
  • Layered fetcher (httpx/Playwright/Chrome CDP) covers most sites without per-site parsers
  • Swappable LLM backend supports cloud vendors, local models, and no-vendor lock-in

Considerations

  • Requires an LLM API key for cloud models or a vision-capable local model for the extraction step
  • Tier-3 fetcher requires the user to launch their own authenticated Chrome browser with remote debugging
  • Brand assets fetched from websites are not covered by the MIT license and are not redistributed

README quick start

Pagewright

LLM-orchestrated e-commerce detail-page (详情页) generator 用通用大模型,一键生成电商商品长图详情页

English · 中文


Demo · 演示

Selling a real product, end to end. Pagewright read the live North Face 1996 Retro Nuptse Jacket page — which is Akamai bot-protected, so curl is blocked and it's fetched through a real browser (tier-3) — pulled the real price, 700-fill down spec, six colorways, sizes and the official benefit ratings + description, then rendered this bilingual 详情页.

Pagewright 读取了 North Face《1996 Retro Nuptse》线上商品页(站点有 Akamai 反爬,curl 被挡 → 经真实浏览器(tier-3)抓取),取到真实价格、700 蓬松鹅绒、6 配色、尺码与官方性能标签及文案, 渲染出这张中英对照详情页

Real copy, specs & pricing shown above; the product photos are heavily mosaicked here to avoid redistributing © The North Face imagery — at run time Pagewright fetches the real photos. Reproduce from examples/north_face_nuptse (add photos per its ASSETS.md). Other bundled example: examples/sa_infinity. 图中文案与数据均为真实信息;产品图已打码处理以规避版权(版权归 The North Face),实拍图在运行时抓取。


English

Give Pagewright a product URL or your own images + a description, and it produces a polished, optionally bilingual long-image — the kind of detail page you upload to Taobao / Tmall / Amazon / Shopify — rendered pixel-accurately from real assets, not AI-painted.

acquire ─▶ extract ─▶ enrich ─▶ compose ─▶ render ─▶ verify
 (URL)      (LLM)    (optional)  (HTML)    (PNG)    (LLM QA)

Why HTML rendering, not text-to-image

An e-commerce detail page lives or dies on data fidelity — the price, the spec numbers, the brand logo and the size chart have to be exactly right. Today's text-to-image / 文生图 models (Stable Diffusion, DALL·E, Midjourney, Flux, Nano-Banana…) are the wrong tool for that job:

  • Text comes out garbled. Generated images mangle words and digits — $159 turns into $IS9, Chinese characters melt into glyph soup. You can't ship a price you can't trust.
  • Logos & icons hallucinate. The model paints a plausible-but-wrong brand mark or tech icon. *(This project's predecessor learned it the hard way: AI-drawn icons that didn't match the bra

Description

LLM-orchestrated e-commerce detail-page generator · 电商出海商品介绍详情页生成

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482