SiliconFlow Qwen Vision

What this skill does

The Python analysis script accepts an image path and prompt for object, scene or screenshot interpretation and can write a text result to a chosen output path. Set OPENAI_API_KEY to a SiliconFlow API key for this workflow; the environment variable name does not mean the request goes to OpenAI. Selected images and prompts are sent to SiliconFlow, so use sensitive material only after the provider’s data terms are approved. Review generated descriptions rather than treating them as verified observations.

Profile published 2026-10-27

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Monthly Trend

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

---
name: siliconflow-qwen-vision
description: 图片理解与分析。当用户需要分析图片内容、识别图片中的物体、描述图片场景、理解图片含义时使用此技能。支持图片问答、物体识别、场景描述等。
---

# 图片理解 (SiliconFlow Qwen2.5-VL)

使用 SiliconFlow 的 Qwen2.5-VL 模型进行图片分析理解。

## 环境配置

- 需要设置 `OPENAI_API_KEY` 环境变量 (SiliconFlow API Key，即 OpenAI 格式的 API Key)
- 或使用 `--api-key` 参数直接传入 API Key

## 使用方法

```bash
cd siliconflow-qwen-vision
python scripts/analyze_image.py -i /path/to/image.jpg -p "请描述这张图片"
```

## 参数说明

- `-i, --image`: 图片路径 (必需)
- `-p, --prompt`: 提示词，默认 "请描述这张图片"
- `-k, --api-key`: API Key (可选，默认从环境变量读取)
- `-o, --output`: 输出文件路径 (可选)

## 示例

```bash
# 描述图片内容
python scripts/analyze_image.py -i photo.jpg -p "这张图片里有什么?"

# 识别物体
python scripts/analyze_image.py -i photo.jpg -p "图片中有哪些物体?"

# 分析场景
python scripts/analyze_image.py -i photo.jpg -p "描述这个场景"

# 保存结果到文件
python scripts/analyze_image.py -i photo.jpg -p "详细描述图片" -o result.txt
```

Popular in AI Agent