Skip to content
CAI
Software that uses CAICheck a score

freestylefly/awesome-gpt-image-2

41.7

Weak · 1 October 2026

11.1k

lines of production code

JavaScript

primary language

2

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

This system is a web-based platform for generating and managing AI images, centered around the GPT-Image2 and GPT-Image2.5 models. It provides a public gallery for browsing styles and a backend infrastructure that handles user credits, memberships, and payments via Alipay. Recent development has focused on stabilizing the billing pipeline, resolving security regressions, and improving local testing capabilities for developers.

How it got here

6 changes.

This period focused on launching the GPT-Image2 prompt gallery site, including the development of a new style library skill for agents and dynamic category mapping. The work involved building the associated Vercel product gallery infrastructure and automating the generation of gallery data. Concurrently, the team removed the legacy built-in template library and visual mappings to streamline the system.

July 2026 — Added local development tools for Alipay sandbox and GA4 authentication

1 change.

Developers can now run a local Alipay sandbox checkout server to test payment flows without affecting production data, and use a new CLI script to authenticate with Google Analytics 4 and retrieve refresh tokens for local environment variables. A Vite plugin has also been added to route local API requests to the corresponding server-side modules, enabling full local testing of community and admin endpoints.

September 2026 — GPT Image 2.5 launch and billing infrastructure

9 changes.

This period centered on the rollout of GPT Image 2.5, establishing the core billing, payment, and generation infrastructure required for the new features. The team expanded the Supabase database schema to support credits and memberships while integrating APIMart GPT-Image-2 generation capabilities. Following the initial launch and community expansion efforts, the work concluded with the resolution of specific security regressions to ensure compliance.

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 41 → 42 (+0.3)
  • Rubric changed (rubric-2026.09.11 → rubric-2026.09.18) — scores are not directly comparable.

Lenses

  • Code Health 28 → 28 (+0.0)
  • Architecture 80 → 76 (-3.4)
  • Maturity 71 → 71 (+0.1)
  • Readiness 41 → 32 (-9.3)
  • Security 54 → 68 (+14.3)
  • Accessibility 77 → 77 (+0.0)
  • Performance 100 (new)

Resolved (5)

  • Dependency hygiene PARTLY measured — npm pinning read, dependency currency not (no pnpm-resolved versions to grade)
  • Documentation: no installation or build instructions (README.md)
  • High CVE: [GHSA redacted] (package-lock.json)
  • Hotspot: api/community/alipay/query.js (api/community/alipay/query.js)
  • Hotspot: src/community.jsx (src/community.jsx)

New (12)

  • High CVE: [GHSA redacted] (package-lock.json)
  • High CVE: [GHSA redacted] (package-lock.json)
  • Outdated (npm): @google-analytics/data
  • Outdated (npm): @supabase/supabase-js
  • Outdated (npm): @vitejs/plugin-react
  • Outdated (npm): google-auth-library
  • Outdated (npm): lucide-react
  • Outdated (npm): react
  • Outdated (npm): react-dom
  • Outdated (npm): stripe
  • Outdated (npm): vite
  • Projects may be oversized for their cohesion

Changes since last survey

  • 1 commits — 1 feature/other, 0 fixes

By area

  • (root) — 1 commit

Notable commits

  • change: docs: add Fluxion AI as project sponsor

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

freestylefly/awesome-gpt-image-2 was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 1 October 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit b93c18ad45397c828fcc39a1ed347830433b3de4 — the exact code this score is about.
  • Scored under rubric-2026.09.18 — the same rubric and the same method as every other entry in this index.
  • Measured by watchdog.canine.dev using codehealth-analyzer preprod-e569280dd5e2.