doubao-image-gen
使用豆包 Seedream 模型文生图,支持并发批量生成,输出图库预览页
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aowind/sjht-doubao-image-genWhat This Skill Does
The doubao-image-gen skill integrates the high-performance doubao-seedream-5-0-260128 model into your OpenClaw environment. This powerful tool allows users to generate high-quality visual content directly through text prompts. It is designed for efficiency, supporting concurrent batch processing for when you need multiple iterations or variations of a concept. Upon completion, the tool organizes your outputs into a clean folder structure, complete with a prompts.json metadata file and an index.html file that serves as an instant gallery for quick visual review.
Installation
To install this skill, run the following command in your terminal within the OpenClaw environment:
clawhub install openclaw/skills/skills/aowind/sjht-doubao-image-gen
Ensure your system meets the requirements: Python 3.8+ and the openai library installed via pip install "openai>=1.0". Once installed, configure your Volcano Engine API Key. You can set this via the ARK_API_KEY environment variable (recommended), a local .env file, or as a command-line argument during execution.
Use Cases
This skill is ideal for rapid prototyping, content creation for social media, or generating reference imagery for creative projects. Whether you need a single specific illustration or a bulk set of artistic variations, the concurrency settings allow you to scale output to match your hardware's capability. It is particularly useful for users who prefer working in a CLI-driven workflow but want the convenience of a browser-based preview gallery.
Example Prompts
- "帮我生成一张赛博朋克风格的上海夜景图,要求分辨率高一些。"
- "画5只不同风格的卡通小猫,我需要做成表情包素材。"
- "请用豆包模型生成一张星空下的草原,尺寸选2K,并把结果保存在当前目录。"
Tips & Limitations
To get the best results, consider optimizing your prompts. While the model accepts Chinese, converting your description to detailed English keywords often yields significantly better artistic results. Remember that the tool defaults to 4 concurrent workers; if you are on a restricted network or low-resource machine, you can adjust the --workers parameter. Ensure you have sufficient disk space when generating large batches, as each image is saved locally. Finally, the tool does not provide direct image hosting, so ensure you access the generated index.html file in your local environment to view your results conveniently.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aowind-sjht-doubao-image-gen": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution
Related Skills
wisdom-forum
世纪智慧论坛自动化技能。支持自动注册、浏览帖子、发布新帖、回复帖子。 论坛地址: http://8.134.249.230/wisdom/
web-screenshot
Capture screenshots of web pages running on local or remote servers using Puppeteer in headless Chromium. Use when user asks to screenshot web pages, capture web UI, take website screenshots, or document web application interfaces. Supports login-required SPAs (Vue/React/Angular) by performing form-based authentication before navigating. Generates screenshots and an optional result.json with per-page descriptions.
data-annotation
通用数据标注处理工具。当用户提到需要数据标注、有标注任务、数据处理、数据集生成、 标注查看/编辑时使用此 skill。支持图像、视频、文本等多种数据类型,调用模型进行内容理解 和标注,生成结构化标注数据,提供 Web 查看编辑界面。 触发短语:「标注」「annotation」「数据集」「label」「tag data」「数据处理」。
long-running-harness
长时程 Agent 项目工作流框架(基于 Anthropic "Effective Harnesses for Long-Running Agents")。 用于创建、管理和调度跨多个上下文窗口的长期项目任务。 Use when: 启动新项目、初始化项目工作流、管理项目任务列表、调度子Agent增量开发、 恢复项目状态、生成项目进度报告。触发短语包括: "启动项目"、"初始化项目"、"创建工作流"、"项目进度"、"继续开发"、 "管理任务列表"、"分配任务"、"next feature"、"project status"。
hair-cam-anno
安防摄像头视频 VL 模型微调数据集标注工具。用于从安防摄像头视频中提取关键帧、分析视频内容、生成结构化标注(含环境/人物/行为/风险描述),并输出符合 dataset.jsonl 格式的微调训练数据。Use when 用户需要对安防摄像头视频进行数据标注、生成 VL 模型训练数据集、处理 /root/hair-cam 目录下的视频数据,或提及 "hair-cam"、"数据标注"、"视频标注"、"VL模型微调"。