# ModelScope Qwen-Image

> Use this tool when you need to generate images from text prompts, particularly for multilingual content creation or as an alternative to Western AI image generation services. It takes text inputs and returns base64-encoded images, handling API communication and error handling automatically. Ideal for AI assistants and applications requiring programmatic access to text-to-image generation capabilities.

Canonical page: https://skillsregistry.net/skills/zym9863-modelscope-qwen-image  
JSON: https://api.skillsregistry.net/v1/skills/zym9863-modelscope-qwen-image

## Description

This MCP server provides text-to-image generation capabilities through integration with ModelScope's Qwen-Image model, built by zym9863 as a Python-based implementation using the MCP framework. The server offers a single tool for generating images from text prompts, handling the API communication with ModelScope's hosted Qwen-Image service and returning generated images as base64-encoded data with automatic format detection and error handling. Built with dependencies including Pillow for image processing, python-dotenv for configuration management, and the official MCP Python SDK, it features environment-based API key configuration and is designed for AI assistants and applications that need programmatic access to Chinese-developed text-to-image generation models, particularly useful for multilingual content creation and scenarios requiring alternatives to Western AI image generation services.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/zym9863-modelscope-qwen-image)
- **Repository:** <https://github.com/zym9863/modelscope-image-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zym9863-modelscope-qwen-image"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zym9863-modelscope-qwen-image` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zym9863-modelscope-qwen-image/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt