MyuriKanao

MyuriKanao / viskit-studio

Public

自托管商品视觉工作台：商品识别、AI 图片生成、二次编辑与电商营销素材套包。

linux.do ai-image-generation creative-automation docker ecommerce fastapi
14
1
89% credibility
Found May 23, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Viskit Studio is an AI-powered product image studio designed for e-commerce marketing teams. It helps users create complete marketing kits by uploading product photos, automatically extracting product information using AI vision, generating 14 professional images (5 hero shots + 9 detail images) or custom output plans, editing images with a built-in tool, and checking marketing compliance. The tool supports both Chinese and English, manages AI provider connections, and provides a dashboard to browse and organize generated kits.

How It Works

1
🚀 You discover Viskit Studio

You hear about an AI tool that creates professional product marketing images automatically.

2
🔑 You connect your AI services

You enter your API keys for AI providers so the tool can think and generate images for you.

3
📸 You upload a product photo

You drag and drop or upload a photo of your product into the tool.

4
✨ AI reads your product automatically

The AI looks at your photo and figures out the product name, brand, category, and selling points on its own.

5
✏️ You review and adjust the details

You see the extracted information and can fix anything the AI got wrong, like changing the product name or adding missing details.

6
You choose your image style
📦
Complete 14-image kit

Get 5 hero images and 9 detail images all at once

🎯
Custom output plan

Pick specific image types you need

7
🎬 Watch your images come to life

You see a real-time progress bar as the AI creates each image, one by one.

8
🖌️ You edit any image you want

If something isn't quite right, you open the built-in editor to change text, adjust colors, or fix specific areas.

9
✅ You see your compliance score

The tool checks your marketing copy and images against rules, showing you a score so you know everything is safe to publish.

🎉 Your marketing kit is ready

You have professional product images and copy, all saved in your catalog, ready to download or publish.

Sign up to see the full architecture

8 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is viskit-studio?

Viskit-studio is a self-hosted visual workbench for e-commerce teams that need to generate, edit, and manage product marketing materials. Upload a product photo and the system extracts product details automatically, then generates a complete marketing kit with hero images, social media assets, and promotional banners. The frontend is a Next.js application with a canvas-based editor for fine-tuning generated images. The backend is a FastAPI service that orchestrates AI image generation, manages a template library, and handles compliance scoring for marketing copy. Everything runs in Docker with SQLite by default or PostgreSQL for production scale.

Why is it gaining traction?

The hook is the end-to-end workflow: upload, extract, generate, edit, and export without leaving a single tool. Many teams cobble together separate services for AI image generation, product data extraction, and graphic editing. Viskit-studio packages these into one deployable unit with a typed API and a web UI. The generation plan endpoint lets you specify templates or let the backend recommend them based on your product description. Built-in compliance checking flags marketing copy issues before assets go live.

Who should use this?

E-commerce operations teams who want to generate marketing assets at scale without relying on third-party SaaS tools. Small to medium brands that need consistent visual output across channels. Developers building internal tools who want a documented API for AI image generation with a ready-made frontend. Not suitable for teams needing a polished, enterprise-ready product out of the box.

Verdict

The concept is solid and the architecture is well-organized, but the project shows its youth: only 14 stars and a credibility score of 0.8999999761581421% signal that adoption is minimal. Test coverage exists but documentation is sparse. If you want to self-host AI image generation with a visual editor, this is worth a closer look, but treat it as an early-stage project and expect to contribute fixes or workarounds.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.