OpenClaw AI 技能

Gemini image generation, editing, and 搜索-grounded image creation via gemini-3.1-flash-image-preview (Nano Banana 2). USE FOR: - Generating images from

生成/edit images via Tuzi API (default), Google Gemini, OpenAI, DashScope, Replicate. Text-to-image + image-to-image editing; 1K/2K/4K resolution. Use f

生成 and edit images with Nano Banana Pro (Gemini 3 Pro Image). And also 50+ 模型s for image generation, video generation, text-to-speech, speech-to-tex..

AI multi-image generation powered by CellCog via Nano Banana. 10-20 coherent images in one prompt, character consistency across scenes, production-gra

Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.

生成/edit images with Gemini 3.1 Flash Image Preview (Nano Banana 2). Direct API call without inference.sh dependency. Use for image 创建/modify reques...

Nano Banana-only image generation on IMA Open API. Supports text_to_image and image_to_image with gemini-3.1-flash-image (bud获取) and gemini-3-pro-imag

生成 and edit images using Google's Nano Banana Pro 模型 via WaveSpeed AI. Supports text-to-image generation and image editing with natural language pro..

Nano Banana Pro with auto 模型 fallback — 生成/edit images via Gemini Image API. 运行 via: uv 运行 {baseDir}/scripts/生成_image.py --prompt 'desc' --filename 'o

Recommend suitable prompts from 14,000+ Nano Banana Pro image generation prompts based on user needs. 优化d for Nano Banana Pro (Gemini), but prompts al

生成 images with Nano Banana Pro via Open路由r. Use when the user asks for image generation, mentions Nano Banana Pro, Gemini 3 Pro Image, or Open路由r imag

生成 AI images with FLUX, Gemini, Grok, 种子ream, Reve and 50+ 模型s via inference.sh 命令行工具. 模型s: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image,...

Free AI text-to-image 生成器 powered by Alibaba's open-source Wan 2.7 模型. No 签名up needed.

生成 social images and OG cards from professional templates via the SnapOG API. One API call = one pixel-perfect PNG.

图像生成辅助。支持通过 Open路由r 直接调用各种生图模型（如 种子ream），为 OpenClaw 优化，支持提示词、尺寸等参数配置。目前仅限 Open路由r 提供者。

使用APIfox图像生成API (jyAPI.AI-WX.CN) 生成图片。支持gpt-image-1.5和grok-4-1-image模型。

生成 images from text descriptions using DALL-E 3 while adhering to usage policies and avoiding rea列出ic human faces.

低成本 AI 图片生成 命令行工具 工具。支持文生图、图片编辑。触发词：生成图片、画图、AI 作图、文生图、图片编辑、imgen。

Automates 上传ing multiple sources (files, URLs, YouTube, Drive, text) to a NotebookLM notebook, generating a deep dive audio overview in a preferred la

日常随笔记录，收录一切想记下来的东西——奇思妙想、灵感片段、日常感想、碎碎念、发现、备忘录，支持图片附件与多图关联。DAIly notes with image attachments and multi-image association support.