发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Tomoviee provides three image generation APIs for reference-based generation, localized editing, and intelligent segmentation.

来自 openclaw/skills 技能

Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations.

``` POST https://ark.cn-beijing.volces.com/api/v3/images/generations ```

> **使命：激发创造，丰富生活** > 让每个人都能用AI实现视觉创意，无需专业技能，只需表达想法。 > > **Mission: Inspire Creativity, Enrich Life** > Empowering everyone to bring visual ideas to life with AI, no expertise required—just share your vision.

Extract text content from images using the Tesseract engine directly via command line.

Automated daily social media posting system that generates content using NewsAPI and UploadPost API with Templated.io image rendering.

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

OpenClaw skill for unified image generation (Midjourney, Flux, SDXL, Nano Banana, Ideogram, Recraft)

This skill enables you to generate images using a variety of state-of-the-art AI models. It supports:

本文档说明如何参与 `image-gen` Skill 的开发与迭代。