character-creator
创建AI角色的完整流程，包括生成详细角色描述、文生图肖像和多角度参考图。使用即梦4.5模型。当用户要求创建角色、生成人物立绘、制作角色参考图、或需要多角度人物图时使用此技能。
Why use this skill?
Automate character design with character-creator. Generate professional AI portraits, 10-view reference sheets, and custom HTML galleries using Seedream v4.5.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/hexiaochun/character-creatorWhat This Skill Does
The character-creator skill is a robust workflow automation tool designed for AI designers and creative developers. It leverages the Seedream v4.5 model (via fal.ai) to transform simple user input into comprehensive character assets. The process is broken into two distinct phases: first, generating a high-quality, professional-grade portrait based on detailed character descriptions; second, producing a 10-view character reference sheet (turnaround) that captures various perspectives including side, back, top, and dynamic poses. All outputs are automatically rendered into responsive HTML files (character-portrait.html and character-gallery.html) for immediate browser previewing.
Installation
To integrate this tool into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/hexiaochun/character-creator
Ensure that your environment has access to the user-sora2-mcp service, as the skill relies on this bridge to communicate with the model provider.
Use Cases
- Game Asset Development: Rapidly prototype character concepts, clothing styles, and facial features for NPCs or playable characters.
- Concept Art Workflow: Generate consistent character model sheets for illustrators to use as a baseline for complex digital paintings.
- Roleplay Support: Create detailed visual documentation for TTRPG characters or virtual avatars.
- Storyboarding: Generate consistent character variations across different camera angles for visual storytelling.
Example Prompts
- "创建一个穿着未来机甲的年轻赏金猎人"
- "生成一个中世纪奇幻风格的精灵游侠，需要全身立绘和多角度参考图"
- "我想制作一个名为艾琳的赛博朋克黑客，请帮我生成她的角色资产"
Tips & Limitations
- Consistency: While the skill attempts to maintain consistency by using the portrait image as a reference (
image_url) for the gallery generation, environmental variables can sometimes lead to slight variations. Always review generated images. - Performance: The process involves 11 separate image generation tasks. Expect the full gallery generation to take approximately 1-2 minutes depending on API queue latency. The skill automatically polls the task status at 5-10 second intervals.
- File Management: The skill writes HTML files to the current project directory. Ensure you have the necessary write permissions in your chosen workspace to avoid errors during the HTML export phase.
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-hexiaochun-character-creator": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api
Related Skills
水浒传故事小人书
水浒传故事小人书创建。使用 Nano Banana Pro 模型生成手绘卡通风格的水浒传故事信息图。当用户想要创建水浒传故事插画、小人书、信息图时使用此 skill。
style-extractor
从参考剧本或参考素材中提取统一风格锚点（STYLE_BASE），确保全剧视觉一致性。当需要匹配参考风格、提取画风、建立风格基准、生成风格资产包时使用。
视频链接解析
解析视频分享链接，获取无水印视频下载地址。当用户想要下载视频、解析抖音/快手/小红书/B站链接、获取无水印视频时使用此 skill。
vidu-video
使用 Vidu Q3 Pro 模型生成视频。当用户想要文生视频、生成带音频的视频，或提到 vidu 时使用此 skill。
image-model-evaluation
评估图像生成模型的效果。对指定模型进行全面的文生图、图生图测试，包括不同参数、不同提示词、人物一致性等测试项，生成详细的HTML测试报告。当用户想要测试、评估、对比图像模型效果时使用此 skill。