Urgent.News

What's breaking now, across thousands of outlets.

AI

How I Added a Free AI Product Photo Generator to a Zero-Budget Toolbox

I run a small AI toolbox for Chinese e-commerce sellers. The whole thing is built with vanilla HTML, one cheap Node server, and free APIs. Last week I added a ninth tool: a product-photo generator that costs $0 per image and needs no API key. Here is the weird part: the hard problem was not image generation. It was getting the model to understand Chinese product descriptions. The stack Static…

A Chinese e-commerce seller created a free AI toolbox for sellers, using vanilla HTML, a cheap Node server, and free APIs. The toolbox now includes a product-photo generator that costs $0 per image and has no API key. The hard part was getting the model to understand Chinese product descriptions. The static frontend is hosted on Netlify, and a small Node HTTP server handles text generation.

Pollinations generates free images without requiring a signup, API key, or credit card. The image endpoint returns a JPEG directly, which can be opened in a browser or fetched server-side. The free tier is rate-limited, returning a yellow image indicating the limit has been reached. To handle this, the tool visually checks the generated image and advises users to wait 45 seconds before retrying.

A translation step converts Chinese product descriptions and scenes into English keywords for better image generation. The final image prompt adds details like clean composition and no text or watermark. Node fetch can sometimes hang, so the tool adds a DNS setting to fix this issue and retries the image request up to four times.

The workflow involves typing a product name and optional scene, translating the scene into English keywords, requesting a 768×768 image, and saving the image with a long-press or right-click. The tool can be improved with optional reference-image upload, queuing requests, and adding background removal after generation. The limitation is clear, and users are warned not to use the output as a fake real shot on a product page.

The tool is free and open-source at https://xiaoshengyi-toolbox.netlify.app/tools/tupian.html?utm_source=devto&utm_medium=social&utm_campaign=tupian.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

I Had Never Written a Line of Code. Then I Shipped a Paid App With AI.

What a complete non-coder in Japan learned building, launching, and charging for a real product using only prompts — and an AI partner. I am not an engineer. Before this project, I had never built an app, never written production code, and honestly, never expected to ship anything that strangers could pay for.

  • Japanese individual with no coding background launches paid AI app, Ippin Log
  • AI tools assist in app development, product management, testing, and research
  • Creator seeds product with personal data by logging 200+ dishes as first user

AWS's Spring AI Agent Blueprint Gets the Boring Parts Right

An agent demo can fit in one class. A production agent needs an answer to harder questions: who can invoke it, what can it remember, which actions require review, how do you trace a bad decision, and what happens when a model call stalls?

  • AWS provides reference architecture for Spring AI agents with Amazon Bedrock
  • Architecture covers agent invocation, data memory, human review, and model failures
  • Separates programming model from managed platform for flexible application design

More from Sunday 15 November →