← 返回
未分类 Key

WuyinKeji GPT-Image-2

Generate images using the WuyinKeji GPT-Image-2 API (速创科技). Supports text-to-image, reference images, multiple aspect ratios, and async result polling. Use w...
通过速创科技的WuyinKeji GPT-Image-2 API生成图像,支持文字生成图像、参考图像、多种宽高比以及异步结果轮询。
alex-shen1121
未分类 clawhub v1.0.0 1 版本 100000 Key: 需要
★ 0
Stars
📥 417
下载
💾 0
安装
1
版本
#latest

概述

WuyinKeji GPT-Image-2 Image Generation

This skill wraps the WuyinKeji (速创科技) GPT-Image-2 async image generation API.

API Endpoints

ActionMethodURL
---------------------
Submit taskPOSThttps://api.wuyinkeji.com/api/async/image_gpt
Query resultGEThttps://api.wuyinkeji.com/api/async/detail?id=&key=

Authentication

  • Header: Authorization:
  • Body: also include "key": "" in JSON payload

1. Submit Generation Task

Request

curl -s -X POST "https://api.wuyinkeji.com/api/async/image_gpt" \
  -H "Content-Type: application/json" \
  -H "Authorization: <API_KEY>" \
  -d '{
    "key": "<API_KEY>",
    "prompt": "Your image generation prompt here",
    "size": "16:9",
    "urls": ["http://example.com/ref.jpg"]
  }'

Parameters

FieldRequiredTypeDescription
------------------------------------
keyYesstringAPI key
promptYesstringGeneration prompt
sizeNostringAspect ratio: auto, 16:9, 9:16, 1:1, 3:2, 2:3 (default: auto)
urlsNoarrayReference image URLs (up to 14 images supported by the model)

Response

{
  "code": 200,
  "msg": "成功",
  "data": {
    "id": "image_xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
    "count": "1"
  }
}

Save the data.id — this is the async task ID.

2. Query Result (Polling)

curl -s "https://api.wuyinkeji.com/api/async/detail?id=<TASK_ID>&key=<API_KEY>"

Response Fields

FieldMeaning
----------------
status: 0Task submitted, waiting to start
status: 1Generating in progress
status: 2Done — check data.result[0] for image URL

Example (completed)

{
  "code": 200,
  "data": {
    "status": 2,
    "result": ["https://openpt1.wuyinkeji.com/xxxx.png"],
    "created_at": "2026-04-22 13:42:01",
    "updated_at": "2026-04-22 13:43:17"
  }
}

3. Download Image

curl -sL "<RESULT_URL>" -o output.png

Typical resolution: 1672×941 (the API output is fixed at this resolution regardless of the size parameter; use the size parameter mainly for aspect ratio hints).

Model Capabilities

  • Text rendering: Good Chinese/English text support in images (prompt explicitly for sharp, readable typography)
  • Reference images: Supports up to 14 reference URLs for style/person consistency
  • Realism: Improved skin texture, hair, facial details over earlier DALL·E models
  • Color accuracy: Reduced yellow/orange color cast compared to DALL·E

Tips for Quality

  1. For sharp text: Explicitly prompt "sharp, crisp, perfectly legible Chinese typography" and specify font style
  2. For person consistency: Include a clear reference photo URL in urls
  3. For billboard/posters: Prompt "billboard quality", "high contrast", "professional advertising photography"
  4. Output resolution is fixed at ~1672×941 — upscaling must be done client-side if 4K is needed

Helper Script

A Bash helper script is available at scripts/generate.sh:

./scripts/generate.sh \
  -k "<API_KEY>" \
  -p "A beautiful sunset over mountains" \
  -s "16:9" \
  -r "http://example.com/ref.jpg" \
  -o "output.png"

The script handles submit → poll → download in one command.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-05-07 06:23 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

Halo Blog

alex-shen1121
用于通过 CLI 管理 Halo 博客实例,包括认证、文章、页面、主题、插件、附件、备份、评论、动态、通知等功能。
★ 0 📥 388

Feishu Group Company

alex-shen1121
配置飞书多机器人公司群,使一个协调机器人(如 company‑ceo)负责处理普通群消息,而专业机器人仅在特定情况下回复。
★ 0 📥 376
communication-collaboration

Feishu Bot Manager CN

alex-shen1121
管理 OpenClaw 中的飞书机器人账户与路由绑定。用于新增飞书机器人账号、把机器人账户级或群聊级绑定到指定 Agent,或在创建新机器人时顺带创建一个全新的独立 Agent 工作区。用户提到“绑定新飞书机器人”“新增飞书机器人”“把机器
★ 0 📥 961