← 返回 Skills 市场

BizyAir 图生图（Image-to-Image）助手

Name: BizyAir 图生图（Image-to-Image）助手
Author: bozoyan

作者 bozoyan · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

274

总下载

当前安装

版本数

在 OpenClaw 中安装

/install bizyair-i2i

功能描述

BizyAir 图生图（Image-to-Image）助手。将本地图片上传后作为参考，使用 AI 生成新的图片。当用户说"根据这张图片生成"、"图生图"、"参考图片生成"、"图片转图片"等时触发。

使用说明 (SKILL.md)

BizyAir 图生图助手

你是一个专业的 AIGC 图生图专家。你帮助用户使用 BizyAir API 将本地图片作为参考，生成新的图片。

核心工作流程

图生图功能需要两步：

上传图片：将本地图片上传到 BizyAir 服务器，获取 URL
生成图片：使用上传的图片 URL 调用图生图 API

支持的功能

图片上传

支持本地图片文件（jpg, png, webp 等格式）
自动上传到 BizyAir 并获取可访问的 URL

图生图生成

web_app_id: 48084 (NanoBananaPro 图生图模型)
参数说明:
- LoadImage.image: 上传后的图片 URL
- BizyAir_NanoBananaPro.prompt: 生成提示词
- BizyAir_NanoBananaPro.aspect_ratio: 图片比例（可选，如 "16:9", "9:16", "1:1" 等）

用户交互流程

第一步：获取图片

当用户发起图生图请求时：

确认用户提供的图片路径
调用上传脚本上传图片
返回上传成功的 URL

第二步：获取提示词

向用户确认生成需求：

期望的图片风格
具体的修改要求
图片比例（可选，默认 16:9）

第三步：创建生成任务

使用 scripts/i2i_workflow.py 完成完整流程：

python3 scripts/i2i_workflow.py \
  --image "/path/to/image.jpg" \
  --prompt "用户提供的提示词" \
  [--aspect-ratio "16:9"]

第四步：查询结果

任务创建后会返回 requestId，告诉用户：

🔖 任务已提交，requestId: \x3CrequestId>
图片正在后台生成，可以让我查询结果

当用户要求查看结果时，使用：

python3 scripts/i2i_workflow.py --query \x3CrequestId>

结果展示格式

生成成功后，使用以下 Markdown 格式展示：

### 🎨 图生图结果
> 🔖 任务 ID: `\x3CrequestId>`
> ⏱️ 生成耗时: `\x3Ccost_time>` 毫秒

| 序号 | 预览 | 图片 URL |
| --- | --- | --- |
| 1 | ![结果1](\x3C图片1的URL>) | \x3C图片1的URL> |

> 📥 如需下载图片，请提供保存路径

错误处理

图片上传失败：检查文件路径是否正确，网络是否正常
API 调用失败：检查 BIZYAIR_API_KEY 环境变量是否配置
生成失败：检查提示词是否符合要求，图片格式是否支持

环境变量

需要配置以下环境变量：

export BIZYAIR_API_KEY="your_api_key_here"

快速开始示例

用户说："根据这张图片生成一个类似的风格"

确认图片路径
上传图片获取 URL
询问具体要求
调用 API 生成
返回结果 URL

安全使用建议

This skill implements the promised image-to-image flow, but you should be cautious before installing or running it: (1) The package metadata omitted required items — the scripts expect a BIZYAIR_API_KEY environment variable and the alibabacloud_oss_v2 Python library; confirm and provide those only if you trust the service. (2) Running the skill will upload your local images to BizyAir and Alibaba OSS (external servers). Do not use sensitive or private images unless you trust BizyAir and understand their data retention/privacy policy. (3) Review the scripts (scripts/i2i_workflow.py and scripts/api.py) yourself — they print and transmit prompt content and perform network calls with your API key. (4) If you need higher assurance, ask the author to correct the registry metadata (declare BIZYAIR_API_KEY and the Python dependency) and provide documentation on token scopes and data handling before proceeding.

功能分析

Type: OpenClaw Skill Name: bizyair-i2i Version: 1.0.0 The skill provides a legitimate integration with the BizyAir Image-to-Image API, enabling users to upload local images and generate AI-modified versions. The main script, `scripts/i2i_workflow.py`, implements a standard workflow: obtaining temporary upload credentials from `api.bizyair.cn`, uploading the file to Alibaba Cloud OSS using the official SDK, and then triggering the generation task. The instructions in `SKILL.md` are clear and aligned with the tool's purpose, and no evidence of malicious intent, data exfiltration beyond the intended service, or obfuscation was found.

能力评估

⚠ Purpose & Capability

The skill's name and description (image-to-image) match the code and SKILL.md: scripts upload a local image and create an I2I task on BizyAir. However the registry metadata lists no required environment variables or primary credential, while both SKILL.md and the code require BIZYAIR_API_KEY; this mismatch between declared metadata and actual needs is inconsistent and should be clarified.

ℹ Instruction Scope

SKILL.md and the scripts instruct the agent to read local image files and upload them to BizyAir (via a token + OSS upload), then create and poll tasks. That behavior is in-scope for an image-to-image skill, but it does mean local files are transmitted to an external service (BizyAir and Alibaba OSS). The instructions do not ask for unrelated files or system credentials beyond the API key.

⚠ Install Mechanism

There is no install spec in the registry and SKILL.md only mentions python3, but the code depends on the alibabacloud_oss_v2 Python package (it exits if missing). The missing declaration of this dependency is an inconsistency (user may be surprised by required pip install). No remote download/install URLs are present, which lowers install risk, but dependency documentation is incomplete.

⚠ Credentials

The code and SKILL.md require a BIZYAIR_API_KEY environment variable (used as a Bearer token) which is appropriate for calling the BizyAir API. However the registry metadata lists no required env vars — an omission. The code also receives temporary OSS access_key/secret/security_token from the service to perform uploads; those are short-lived and provided by the remote API (expected for this flow).

✓ Persistence & Privilege

The skill is not always-on and is user-invocable (defaults). It does not request persistent presence or modify other skills or system-wide config. It runs as a standalone script invoked by the agent or user.

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 bizyair-i2i
安装完成后，直接呼叫该 Skill 的名称或使用 /bizyair-i2i 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

v1.0.0

bizyair-i2i v1.0.0 - Initial release of BizyAir 图生图（Image-to-Image）助手。 - Allows users to upload local images and generate new ones using BizyAir API with image-to-image models. - Supports image upload (jpg, png, webp), prompt-based generation, and result preview via Markdown. - Provides full user guidance for image selection, prompt entry, and result display. - Includes error handling for uploads, API calls, and generation failures.

元数据

Slug bizyair-i2i

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题