mrkeyoor.comAsk

freestylefly/awesome-gpt-image-2tested 27 Sept 2026commit b93c18a

awesome-gpt-image-2 review

Our Awesome GPT Image 2 run passed all 40 tests, but npm audit reported 8 known vulnerabilities, including 6 high-severity findings, so hosting its generation website needs further dependency review.

  • Install 12 s
  • Build 16 s
40/40tests passed
  • 276 packages
AI Toolsevaluationupdated 28 Sept 2026
+153stars / 7d

Awesome GPT Image 2 is a prompt and example-image library whose core template guide is mainly Chinese, with English and Japanese READMEs available. It helps you describe layouts and visual styles more precisely, through copyable templates, an agent skill, and a gallery website with generation features.

Verdict

Our Awesome GPT Image 2 run passed all 40 tests, but npm audit reported 8 known vulnerabilities, including 6 high-severity findings, so hosting its generation website needs further dependency review. Use the gallery or agent skill when you need reusable visual instructions. Resolve the documented setup gaps before taking on its authentication and billing services.

We ran it

Lab card: what happened when we ran awesome-gpt-image-2
Lab card from our sandbox run
Screenshot of awesome-gpt-image-2 (gpt-image2.canghe.ai)
gpt-image2.canghe.ai
Install✓ · 12s276 packages · 169 MB
Build✓ · 16s
Tests✓ · 9s40 passed · 0 failed of 40 (node:test)
Known vulns80 critical · 6 high · 2 moderate · 0 low (npm audit)
Repo725 files~13,093 lines of source · 189.6 MB · 1 CI workflows

Answers from our run

Does awesome-gpt-image-2 build from source?

Dependencies installed in 12 seconds (276 packages), and the build succeeded in 16 seconds. We cloned commit b93c18a into a clean Debian container with 3 CPUs and no project-specific setup.

Do awesome-gpt-image-2's tests pass?

Yes. The project's own test command finished in 9 seconds and reported 40 passed, 0 failed (node:test).

Does awesome-gpt-image-2 have known vulnerabilities in its dependencies?

npm audit flagged 8 known advisories in the dependency tree at the time of our run.

Who should not use awesome-gpt-image-2?

Teams needing an offline image model: the documented website generation uses APIMart, and the skill returns prompts rather than running a model.

What are the alternatives to awesome-gpt-image-2?

Awesome GPT-4o Images, ComfyUI. Our Awesome GPT Image 2 run passed all 40 tests, but npm audit reported 8 known vulnerabilities, including 6 high-severity findings, so hosting its generation website needs further dependency review.

Setup3/5Browsing is simple; hosting adds Supabase, APIMart, and billing setup
Docs3/5Useful templates; Chinese core guide and open deployment omissions
Community4/5October push and recent PR activity, with setup reports still open
Maturity3/540 checks passed; 8 audit findings and unresolved setup reports

Who it’s for

Designers and developers who want a concrete layout or composition to adapt before writing an image prompt.
Claude Code users who want an agent to choose templates from the same structured library the website uses.
Teams making repeated infographics or product visuals who can translate Chinese guidance and inspect generated text.
Developers prepared to configure Supabase and APIMart if they actually need to operate the generation website.

Who it’s NOT for

Teams needing an offline image model: the documented website generation uses APIMart, and the skill returns prompts rather than running a model.
English-only teams expecting every guide to be translated: the main README is English, but the core template guide is mainly Chinese.
Agencies needing commercially cleared stock assets: the README explicitly declines to guarantee commercial rights to collected content.
Operators expecting a complete deployment checklist: open issues 48 and 44 identify missing migration instructions and Watcha login settings.
Teams requiring a dependency audit with no known advisories: our sandbox reported 8 vulnerabilities, including 6 high-severity findings.

Setup reality

Our sandbox installed commit b93c18a in 12 seconds, adding 276 npm packages and using 169 MB on disk. The build passed in 16 seconds, and node:test passed all 40 tests in 9 seconds, with 0 failures. Npm audit reported 8 known vulnerabilities: 6 high and 2 moderate, with 0 critical and 0 low. We ran it on September 27, 2026, with 3 CPUs and 8 GB RAM in an unprivileged Debian lab-node:22 container without secrets.

Reading prompts needs no local server. Website generation uses APIMart through a personal browser API key or Supabase sign-in, credits, and a server-side provider key. Hosting requires the relevant database migrations and authentication redirects. Stripe billing adds server secrets and webhooks, while Alipay has separate setup instructions.

The Vite frontend and Vercel API handlers need different hosting support, so serving the static output alone does not provide generation or billing endpoints. Open deployment reports identify missing migration and Watcha configuration instructions. Our scan found 1 CI workflow file, no Dockerfile, and no tests directory. The main template guide is largely Chinese.

Start with a prompt template before hosting the website

Open the UI template and you're asked to specify the platform, layout, exact text, and aspect ratio. That's a useful starting point when your image request amounts to "make a product screenshot." Awesome GPT Image 2 collects visual examples and turns recurring instructions into templates. The core guide is mainly Chinese, although English and Japanese READMEs exist and gallery entries include English prompts. English readers can use it, but should expect translation work. Browsing the repository or its public gallery needs no local application. That matters because our checkout occupied 189.6 MB before installation. You can learn from the examples without taking on the website's authentication and billing code.

The template guide is the better entry point for repeated work: its UI example separates content and layout constraints in JSON, making each variable easier to change deliberately.

What happened when we ran it

Our sandbox installed commit b93c18a in 12 seconds, adding 276 npm packages and using 169 MB on disk after installation. The build succeeded in 16 seconds. We ran the repository on September 27, 2026, in a fresh Debian container using image lab-node:22, with 3 CPUs and 8 GB of RAM. The container was unprivileged and had no secrets. These are repository setup measurements, not image-generation benchmarks.

The node:test run passed all 40 tests in 9 seconds, with 0 failures. Our scan found 1 CI workflow file, no Dockerfile, and no tests directory. Tests can live beside source files, so the missing directory doesn't contradict the result. A successful suite tells you that the executed checks passed in this environment. It doesn't establish that a deployed login, payment, or image-generation flow works with real credentials.

Npm audit reported 8 known vulnerabilities: 6 high and 2 moderate, with 0 critical and 0 low. The checkout contained 725 files and roughly 13,093 lines of source. The audit summary doesn't identify the affected dependency paths or demonstrate an exploitable public endpoint. Anyone deploying the application should inspect those advisories before exposing it. Reading prompt files requires a different commitment from operating the code that surrounds them.

The Claude Code skill returns a prompt you still have to generate

The included skill reads a reference generated from data/style-library.json, the same library used by the website. Its workflow chooses a category, matches style and scene tags, and returns a copyable prompt with the selected template and useful case references. That gives a coding agent concrete material to consult.

For a repeated request, such as a product infographic, the reference keeps the agent tied to named examples instead of whatever style it remembers. The README provides a Claude Code marketplace route and a separate CLI that copies the skill into local agent folders. Read the destination list before using install all, since it writes beyond the current project. Our 40 passing code tests don't measure whether the resulting prompts improve generated images. The skill's documented output is a prompt. You'll still need an image-generation tool, and you'll still need to inspect the picture it returns.

Running generation adds Supabase and APIMart

The website's documented generation routes use APIMart. A personal API key stays in the browser under the README's described route, while users without one go through Supabase sign-in, platform credits, and a server-side provider key. The website setup checklist names database migrations and authentication redirects. Payment features add Stripe secrets and webhook configuration, with separate instructions for Alipay. This is substantial application setup for someone who only wanted a prompt catalog.

A 16-second build doesn't settle those service requirements. Vercel configuration builds the Vite frontend into dist, while server handlers live under api/. Copying the static output alone won't provide those handlers. Keep the Supabase service-role credential and Stripe secrets on the server, as the README instructs. For a private reference library, I'd begin with browsing or the skill and leave the paid generation application until there's a concrete reason to operate it.

The MIT license doesn't clear every gallery image

The README licenses the project under MIT, then separately warns that it cannot guarantee commercial rights to collected prompts and example images. It names community sources and tells commercial users to obtain permission from original rights holders. That distinction matters if you're collecting campaign assets for a client. A gallery example can teach composition without giving you permission to reuse the example itself. Follow its source link before treating it as licensed stock.

For a commercial brief, I'd borrow the layout instructions and substitute your own subject and copy before generating an original draft. Even then, check the output. The template guide asks for readable labels and fixed layouts, but those instructions are requests to a model. Our sandbox measured the repository's code checks, so it supplies no evidence that every requested word or layout survives generation.

October activity hasn't resolved the documented setup gaps

GitHub recorded the last push on October 14, 2026, with 34,545 stars and 33 open issues and PRs when checked. Recent activity includes a closed image-cache hardening PR. Meanwhile, issue 48 reports missing migration instructions, and issue 44 identifies undocumented Watcha login configuration. Both remain open, alongside proposed fixes. These concern this website's deployment, making them worth reading before following its checklist literally.

The latest-release endpoint returned no release, which doesn't outweigh the recent push and contribution activity. For another example collection, compare jamez-bondos/awesome-gpt4o-images. For locally executed image workflows, consider ComfyUI. I'd use Awesome GPT Image 2 to find and adapt a template today. Before hosting its generation service, I'd resolve the setup reports and inspect the 8 audit findings from our run. Copying a useful prompt shouldn't commit you to running a payment system.

Alternatives

ProjectWhat it isPick it when
Awesome GPT-4o ImagesA curated collection of GPT-4o and gpt-image-1 images with source links and prompts.pick this instead when you want another image-and-prompt reference collection, especially for GPT-4o or gpt-image-1 examples.
ComfyUI gh↗A visual node editor and execution engine for reusable image-generation workflows.pick this instead when you need to run local models and control an executable workflow, and can manage the models and hardware.

What people are saying

  1. [github-trending] freestylefly/awesome-gpt-image-2

Sources

  1. Project README, generation setup, and content disclaimer
  2. Prompt templates and pitfalls guide
  3. Style-library agent skill and output instructions
  4. Issue 48: missing database migration instructions
  5. Issue 44: undocumented Watcha login configuration
  6. Current repository metadata from GitHub
  7. Awesome GPT-4o Images repository
  8. ComfyUI repository and workflow documentation

More ai tools reviews