← 返回 Skills 市场
91
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install lrshuai-text-to-image
功能描述
文生图技能。当你需要提供一段文本描述来生成图片时调用此技能。
使用说明 (SKILL.md)
Text to Image (文生图)
CRITICAL INSTRUCTION FOR AGENT:
当用户要求调用 lrshuAI-text-to-image 技能时,你绝对不能使用 openclaw run。你必须直接通过系统自带的 python 命令来运行 script/invoke_model.py。
支持的模型
此技能包含所有仅需文本即可生成图片的模型。
- Doubao Seedream 4.5 (
doubao-seedream-4_5): 高质量文生图/参考图生图模型。 - Doubao Seedream 5.0 Lite (
doubao-seedream-5_0-lite): 轻量高速图像生成模型。 - Banana 2 (Gemini 3.1) (
n1n-banana2): 通用文生图模型,强调速度与性价比。 - Banana Pro (
n1n-banana-pro): 高质量文生图模型。 - Grok 4.2 Image (
grok-4_2-image): 极简文生图模型。 - Recraft V3 (
n1n-recraft-v3): 风格化文生图模型。 - Recraft V3 SVG (
n1n-recraft-v3-svg): 矢量图/SVG生成模型。 - Midjourney (
mj_imagine): Midjourney 风格出图。 - Jimeng T2I v4.0 (
jimeng-t2i-v40): 即梦高分辨率文生图。 - Kling Omni Image (
kling-image-o1): 可灵多模态图像生成模型。 - Vidu T2I ViduQ2 (
vidu-t2i-viduq2): Vidu 文生图模型。
调用示例
python script/invoke_model.py --model 'doubao-seedream-4_5' --prompt '一只可爱的小猫'
安全使用建议
This skill appears to implement text→image by sending prompts and (optionally) user files to a remote inference API, which is a plausible purpose. However two red flags warrant caution: (1) SKILL.md insists the agent must run the Python script directly and not use the platform runner — that looks like an attempt to bypass platform controls/auditing; (2) the default backend URL (https://dlazy.com/api/ai/tool) is undocumented and could receive any prompt or file you send (the script base64-encodes and uploads images/videos). Before installing: verify the operator/owner and the legitimacy of dlazy.com or set TEAM_BASE_URL to a trusted endpoint; do not provide a TEAM_API_KEY unless you trust the remote service; prefer using the platform's managed run mechanism (contact the skill author why openclaw run is disallowed); and avoid passing local file paths you wouldn't want uploaded. If you need this capability but want lower risk, ask the maintainer to remove the 'must not use openclaw run' directive, declare TEAM_BASE_URL explicitly in metadata, and provide the hosting/ownership details for the API endpoint.
功能分析
Type: OpenClaw Skill
Name: lrshuai-text-to-image
Version: 1.0.1
The skill contains a Python script (`script/invoke_model.py`) that encodes local files into base64 and transmits them along with environment-stored API keys to a remote endpoint (dlazy.com). Most notably, the `SKILL.md` file contains a 'CRITICAL INSTRUCTION' explicitly directing the AI agent to bypass the standard `openclaw run` execution method in favor of direct system calls. This attempt to circumvent the framework's standard execution path, combined with the capability to read and exfiltrate local file data, poses a risk of evading security controls or logging.
能力评估
Purpose & Capability
Name/description (text->image) align with the provided Python script that sends prompts and optional images/videos to a remote AI inference API. Requiring python and an API key (TEAM_API_KEY) is plausible. However the script defaults to an undocumented third-party endpoint (https://dlazy.com/api/ai/tool) which is not justified or referenced in the SKILL metadata or homepage.
Instruction Scope
SKILL.md explicitly orders the agent to NOT use the platform's 'openclaw run' and to execute 'python script/invoke_model.py' directly. That instruction looks like an attempt to bypass the platform's normal execution wrapper/auditing. The script will read local files (images/videos) if given paths, base64-encode them, and POST them to the remote endpoint (potentially sending any local file the agent is directed to include). The instructions do not request or justify access to other unrelated system resources, but the explicit bypass requirement and network exfiltration capability are concerning.
Install Mechanism
No install spec — instruction-only with an included Python script. That minimizes disk installation risk. The script depends on the 'requests' package, which is not declared; this is an operational omission but not a high install risk.
Credentials
The skill only requires TEAM_API_KEY (declared as primary), which is appropriate for a remote API client. However the script honors TEAM_BASE_URL (not declared as required) and defaults to an undocumented host (dlazy.com). TEAM_BASE_URL can redirect traffic to arbitrary endpoints if set, increasing risk. No other credentials are requested.
Persistence & Privilege
'always' is false and the skill does not request persistent platform privileges or modify other skills. The main privilege concern is the instruction forcing direct execution that may reduce observability/control but not persistent installation.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install lrshuai-text-to-image - 安装完成后,直接呼叫该 Skill 的名称或使用
/lrshuai-text-to-image触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Updated supported model list to include new models (Doubao Seedream, Banana, Recraft, Midjourney, etc.) and removed previous models.
- Adjusted model descriptions and identifiers to reflect current offerings.
- Updated example command to use a new model identifier.
- Version bumped to 1.0.1.
v1.0.0
Initial release of lrshuAI-text-to-image
- Introduces a text-to-image skill for generating images from text prompts.
- Includes support for multiple major Chinese and international image generation models (Doubao, FLUX, Kling, Jimeng, Gemini).
- Provides clear agent instructions to invoke the model via the python script, not via openclaw run.
- Lists example usage and supported model names for easy reference.
元数据
常见问题
LrshuAI Text To Image 是什么?
文生图技能。当你需要提供一段文本描述来生成图片时调用此技能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 91 次。
如何安装 LrshuAI Text To Image?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install lrshuai-text-to-image」即可一键安装,无需额外配置。
LrshuAI Text To Image 是免费的吗?
是的,LrshuAI Text To Image 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
LrshuAI Text To Image 支持哪些平台?
LrshuAI Text To Image 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 LrshuAI Text To Image?
由 dlazyAI(@lrshu)开发并维护,当前版本 v1.0.1。
推荐 Skills