Ce Gemini Imagegen
技能 活跃This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
To provide a comprehensive interface for creating and manipulating images programmatically using the Gemini API, catering to a wide range of visual content needs.
功能
- Text-to-image generation
- Image editing with text instructions
- Multi-turn refinement of generated images
- Composition from multiple reference images
- Customizable resolution and aspect ratio
- Google Search grounding for real-time data integration
使用场景
- Creating unique images from text prompts
- Editing existing photos to add or modify elements
- Generating stylized art or logos
- Producing product mockups or stickers
- Iteratively refining image concepts through conversation
非目标
- Replacing dedicated image editing software for complex pixel-level manipulation
- Generating images without an API key
- Performing operations beyond image generation and editing
Security
- warning:Secret ManagementThe skill requires a `GEMINI_API_KEY` environment variable, but the documentation does not explicitly detail how to securely manage or set this key, nor does it mention potential risks of exposing it.
Trust
- warning:Issues AttentionThere are 25 open issues and 115 closed issues in the last 90 days, resulting in a closure rate of approximately 82%, which is good, but the high number of open issues suggests potential maintainer bandwidth issues.
安装
请先添加 Marketplace
/plugin marketplace add EveryInc/compound-engineering-plugin/plugin install compound-engineering@compound-engineering-plugin质量评分
类似扩展
Qwen Edit
100AI图像编辑的Qwen-Image-Edit提示模式。用于在编辑照片时保留身份、重新构图裁剪的图像、更换服装或配饰、调整姿势、应用风格转换或角色转换。提供提示模式、参数调整和示例。
Generate Social Media Book Promo
100Generate a vertical story image for TikTok or Instagram book promotion with cover art, hook text, and author branding.
Generate Real Estate Listing Graphic
100Generate a branded property listing graphic with a property photo, status badge, price, address, and key stats.
Baoyu Comic
100Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
产品摄影工作流
100多角度产品影像工作流。当用户想要“拍摄产品”、“制作电商产品图”、“产品摄影集”、“电商产品图”、“产品多角度图”、“品牌产品视觉效果”，或提供单张产品照片并要求营销级变体时使用。从一张参考图像生成4个不同的方向（生活场景、微距细节、比例/上下文、营销布局）。不适用于：肖像、通用插图、徽标设计、视频创作——请使用其他技能或直接调用generate_image。
Openclaw
100使用多提供商路由从文本生成图像和视频 — 支持 GPT Image 2.0（近乎完美的文本渲染）、Nanobanana 2、Seedream 5.0、Midjourney V8.1（统一的逼真+动漫风格）、Flux 2 Klein（经济高效的草稿）、Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 视频，以及本地 ComfyUI 工作流。包含 1,446 个精选提示和风格感知提示增强。当用户想要创建图像/视频、设计素材、制作照片动画、增强提示或管理 AI 艺术工作流时使用。不适用于：通用聊天、代码生成、文档编写、现有素材的视频编辑、音频/TTS，或任何与 AI 图像/视频创建无关的任务。