awesome-gpt-image-2/docs/CONTRIBUTING.md
Jared Liu a00a14c74f feat: scaffold awesome-gpt-image-2 from nano-banana-pro template
Mirror of awesome-nano-banana-pro-prompts tuned for OpenAI's upcoming
GPT Image 2 (codename "duct-tape"):

- Swap CMS model filter to gpt-image-2 + campaign gpt-image-2-prompts
- i18n.ts: all 16 languages rebranded; rewrite seedancePromo to
  cross-promote nano-banana-pro, and whatIs content to reflect
  GPT Image 2's actual strengths:
    * Pixel-perfect multi-language text rendering (zh/en/ja)
    * Cross-image pixel-level consistency
    * Commercial-ready illustration quality
    * True art style induction
  Primary languages (en, zh, zh-TW, ja, ko) hand-translated;
  others fall back to English copy (will be refined later)
- markdown-generator: cover image path switched to
  gpt-image-2-prompts-cover-{en,zh}.png, arenaUrl points at the
  gallery page (the side-by-side arena page doesn't exist yet)
- GitHub Actions:
    * update-readme.yml runs on cron 0 0,12 * * * (twice daily
      per product request, instead of every 4 hours)
    * sync-approved-to-cms.yml wired to gpt-image-2 model
- Cover images, issue templates, docs, LICENSE (year 2026) updated
- Initial 16 README_*.md files generated from live CMS (78 prompts,
  44 categories) so the repo renders immediately without waiting
  for the first Action run

Secrets the repo needs before the Action runs on the remote:
  - CMS_HOST
  - CMS_API_KEY

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-20 14:42:24 +08:00

3.4 KiB

🤝 Contributing to Awesome GPT Image 2 Prompts

Thank you for your interest in contributing! This guide will help you submit your prompts.

📋 Table of Contents

🚀 How to Contribute

GitHub Issue

We only accept contributions via GitHub Issues to ensure quality control and consistent formatting.

  1. Click Submit New Prompt
  2. Fill in the form with all required information
  3. Submit your issue
  4. Team reviews within 48 hours
  5. If approved (we add approved label), it automatically syncs to CMS
  6. Your prompt appears in README within 4 hours

Why Issues only?

  • Consistent formatting
  • Better quality control
  • Automated processing
  • Lower barrier to entry

📝 Submission Guidelines

Required Information

  • Title: Clear, descriptive (max 80 characters)
  • Prompt: The full prompt text
  • Description: What it does, when to use it
  • Images: One or multiple high-quality results (one URL per line)
  • Author: Original creator's name and link
  • Source: Link to original post/tweet
  • Language: Prompt's language (supports 17 languages)

Image Requirements

  • Multiple images supported: Add one URL per line
  • Minimum width: 512px
  • Recommended: 1024px - 2048px
  • Formats: JPEG, PNG, WebP
  • File size: < 5MB per image
  • No watermarks (except original author's)

Supported Languages

English, Chinese (简体中文), Traditional Chinese (繁體中文), Japanese (日本語), Korean (한국어), Thai (ไทย), Vietnamese (Tiếng Việt), Hindi (हिन्दी), Spanish (Español), Latin American Spanish (Español Latinoamérica), German (Deutsch), French (Français), Italian (Italiano), Brazilian Portuguese (Português do Brasil), European Portuguese (Português), Turkish (Türkçe)

Quality Standards

We accept prompts that are:

  • Original or properly attributed
  • High-quality results
  • Clear and reproducible
  • Creative and inspiring
  • Safe for work

We reject:

  • Low-quality or blurry images
  • Plagiarized content
  • NSFW content
  • Harmful or offensive material
  • Spam or promotional content

📜 License Agreement

By contributing, you agree to:

  1. License: Your contribution will be licensed under CC BY 4.0
  2. Attribution: Proper credit will be given to original authors
  3. Rights: You confirm you have the right to submit this content

🔄 Review Process

  1. Submission → User creates GitHub Issue
  2. Review → Team checks quality (within 48h)
  3. Approval → Team adds approved label
  4. Auto-sync → Workflow triggers, creates prompt in CMS
  5. README Update → Appears in README (next 4h update)

Questions?


Thank you for helping make this the best GPT Image 2 resource! 🙏