OpenClaw

zenmux-image-generation

Generate images via ZenMux API (Pro/Elite). Supports Text-to-Image, Image-to-Image, and Multi-Image reference fusion.

dadaniya990 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install dadaniya99/zenmux-image-generation

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

ZenMux Image Generation Skill (Gemini 3 Pro)

This skill uses the ZenMux API to generate high-fidelity images using the Gemini 3 Pro Image (Nano Banana Pro) model.

Features

Text-to-Image: Generate visuals from descriptive prompts.
Image-to-Image: Modify an existing image based on a prompt.
Multi-Image Fusion: Combine elements or styles from multiple reference images (e.g., character from one image, costume/style from another).

Usage

To generate an image, execute the scripts/generate.py script.

IMPORTANT:

You must set the ZENMUX_API_KEY environment variable.
Model: Defaults to google/gemini-3-pro-image-preview.
Provider: ZenMux (Requires Pro or higher plan).

1. Text-to-Image

ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "a cybernetic lobster in space"

2. Image-to-Image

ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "make it winter" --images "summer.png"

3. Multi-Image Fusion (Advanced)

ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "put this child in this costume" --images "child.png" "costume.jpg"

Arguments

--prompt (required): Text description of the task.
--images (optional): Path(s) to one or more reference image files.
--model (optional): Defaults to google/gemini-3-pro-image-preview.
--output (optional): Defaults to generated_image.png.

来源信息

Source: github
Repository: openclaw/skills
Path: skills/dadaniya99/zenmux-image-generation
Version: —
Commit: b75467c237024ed777e735f3c0a890a14ace9856
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# ZenMux Image Generation Skill (Gemini 3 Pro)

This skill uses the ZenMux API to generate high-fidelity images using the **Gemini 3 Pro Image (Nano Banana Pro)** model.

## Features

*   **Text-to-Image**: Generate visuals from descriptive prompts.
*   **Image-to-Image**: Modify an existing image based on a prompt.
*   **Multi-Image Fusion**: Combine elements or styles from multiple reference images (e.g., character from one image, costume/style from another).

## Usage

To generate an image, execute the `scripts/generate.py` script.

**IMPORTANT:**
*   You must set the `ZENMUX_API_KEY` environment variable.
*   **Model**: Defaults to `google/gemini-3-pro-image-preview`.
*   **Provider**: ZenMux (Requires **Pro** or higher plan).

### 1. Text-to-Image
```bash
ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "a cybernetic lobster in space"
```

### 2. Image-to-Image
```bash
ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "make it winter" --images "summer.png"
```

### 3. Multi-Image Fusion (Advanced)
```bash
ZENMUX_API_KEY="YOUR_KEY" python3 scripts/generate.py --prompt "put this child in this costume" --images "child.png" "costume.jpg"
```

### Arguments

*   `--prompt` (required): Text description of the task.
*   `--images` (optional): Path(s) to one or more reference image files.
*   `--model` (optional): Defaults to `google/gemini-3-pro-image-preview`.
*   `--output` (optional): Defaults to `generated_image.png`.

搜索