wuyin-gpt-image2Generate 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...
Install via ClawdBot CLI:
clawdbot install alex-shen1121/wuyin-gpt-image2Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.wuyinkeji.com/api/async/image_gpt`Calls external URL not in known-safe list
https://api.wuyinkeji.com/api/async/image_gpt`Audited Apr 23, 2026 · audit v1.0
Generated Oct 1, 2026
Online sellers can generate polished product images from simple text prompts or reference photos, covering categories like fashion, electronics, and home goods. With 14 reference images supported, sellers keep the same product shape and style across an entire catalog without a photoshoot.
Marketing teams can rapidly produce billboard-quality posters, banner ads, and social media visuals with sharp, legible Chinese and English typography. The API's strong text rendering and reduced color cast make it suitable for brand-consistent campaign assets.
Creators on platforms like Xiaohongshu, WeChat, and Douyin can generate eye-catching cover images, meme-style graphics, and illustrated posts. Native Chinese text support means captions and titles render clearly without post-editing.
Game developers and illustrators can iterate quickly on character designs, environments, and item art using reference images for person consistency. Multiple aspect ratios (16:9, 1:1, 9:16) fit everything from loading screens to mobile portraits.
Small businesses selling custom t-shirts, mugs, and posters can generate artwork on demand and fulfill orders without maintaining an image library. Automated submit-poll-download workflows allow integration into storefront ordering systems.
Bundle WuyinKeji GPT-Image-2 alongside other image models behind a unified API, offering developers a single key and billing dashboard. Adds value through unified rate limits, fallback routing, and usage analytics.
Wrap the API in a web app with templates, brand kits, and collaborative editing for SMB marketing teams. Users pay for credits or seats, while the platform handles prompt optimization and asset management.
Offer managed image generation as a service—clients submit briefs, the agency returns finished ad creatives, poster sets, and product visuals. Leverages the API's text rendering and reference-image consistency to deliver brand-safe output at scale.
💬 Integration Tip
Submit the task with both the Authorization header and the body 'key' field, then poll the detail endpoint until status equals 2—remember output is fixed at ~1672×941, so plan client-side upscaling for 4K needs.
Scored Jun 14, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。