← Back to Skills Marketplace
bozoyan

BizyAir 图生图（Image-to-Image）助手

by bozoyan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
274
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install bizyair-i2i
Description
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。
README (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：

  1. 上传图片：将本地图片上传到 BizyAir 服务器，获取 URL
  2. 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：

  1. 确认用户提供的图片路径
  2. 调用上传脚本上传图片
  3. 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"

  1. 确认图片路径
  2. 上传图片获取 URL
  3. 询问具体要求
  4. 调用 API 生成
  5. 返回结果 URL
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
⚠ 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.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install bizyair-i2i
  3. After installation, invoke the skill by name or use /bizyair-i2i
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
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.
Metadata
Slug bizyair-i2i
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is BizyAir 图生图（Image-to-Image）助手?

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。 It is an AI Agent Skill for Claude Code / OpenClaw, with 274 downloads so far.

How do I install BizyAir 图生图（Image-to-Image）助手?

Run "/install bizyair-i2i" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is BizyAir 图生图（Image-to-Image）助手 free?

Yes, BizyAir 图生图（Image-to-Image）助手 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does BizyAir 图生图（Image-to-Image）助手 support?

BizyAir 图生图（Image-to-Image）助手 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created BizyAir 图生图（Image-to-Image）助手?

It is built and maintained by bozoyan (@bozoyan); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463942 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259883 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200739 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191401 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190375 · by oswalpalash

💬 Comments