# CookSleep/gpt_image_playground

基于 OpenAI gpt-image-2 API 的图片生成与编辑工具

Repository: https://github.com/CookSleep/gpt_image_playground
Canonical: https://ross.abutalabs.com/products/gpt_image_playground
Homepage: https://gpt-image-playground.cooksleep.dev
Language: TypeScript
License: MIT
License Family: permissive
Topics: gpt-image, image-editing, image-generation, openai, react, tailwindcss, typescript, vite
Last push: 2026-08-26T05:39:40+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 9
- inputs: {"age_days": 132, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 77}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3549, forks 889 (observed 2026-08-28T04:08:09.463668+00:00)

## What it is
A web-based playground for generating and editing images via the OpenAI gpt-image-2 API, built with React, TypeScript, and Tailwind CSS. It supports OpenAI-compatible endpoints, fal.ai, custom HTTP providers, reference-image and mask editing, and stores all data locally in the browser.

## Use cases
- generate images from text prompts with gpt-image-2
- edit images using reference images and masks
- use OpenAI-compatible or custom API providers for image generation
- keep image generation history and parameters locally in the browser
- deploy a personal AI image generation web UI on Vercel or GitHub Pages

## When to choose
- you want a ready-made web UI for OpenAI image generation and editing APIs
- you need support for multiple or custom image API providers
- you prefer local-only storage of history and settings without a backend

## When to avoid
- you need server-side batch image generation or automation
- you want a desktop or mobile native app
- you need image models from providers not reachable via OpenAI-compatible HTTP APIs

## Facets
- artifact type: application
- maturity: active
- function: image-processing, llm-inference, http-client, ui-components
- domain: artificial-intelligence, image-processing, web-development, frontend
- platform: cross-platform, browser
- tags: openai, gpt-image, image-generation, image-editing, react, typescript, vite, tailwindcss, local-storage, text-to-image, web-server

## Member repositories
- CookSleep/gpt_image_playground (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:09.463668+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:34:22.016621+00:00, confidence not recorded.
  - readme: https://github.com/CookSleep/gpt_image_playground (fetched 2026-08-28T04:08:09.463668+00:00, sha d14f2edddca0)
  - homepage: https://gpt-image-playground.cooksleep.dev (fetched 2026-08-29T09:28:41.430414+00:00, sha 6c1ff7ae1e19)
- Data as of 2026-08-30T08:39:29.467469+00:00.