iconben/z-image-studioMCPMCP Server

z-image-studio

A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)

115stars

10forks

Python

aiappleapple-siliconcudadiffuserslocalllmloramcp-servermpspythonrocmtext-to-image

Quality signals

ActiveNo testsNo CIThin docsNo licensePopular

Open Repository Download ZIP

AI summary

Auto-generated overview of what this skill does and when to reach for it.

Local text-to-image generator with CLI, web UI, and MCP server for Z-Image-Turbo models optimized for multiple GPUs.

Use this when

Need fast image generation without cloud APIs
Working offline or with sensitive prompts
Running on NVIDIA/AMD/Intel/Apple Silicon GPUs
Integrating image generation into AI agents via MCP
Managing multiple LoRAs with per-LoRA strength control

Don't use when

Need cloud-based generation with no local setup
Running on unsupported hardware (e.g., non-GPU Windows AMD)
Requiring real-time generation for high-volume production

Capabilities

CLI for direct terminal image generation
Web UI with history browser and hardware-aware model selection
MCP server for AI agent integration (stdio/SSE/HTTP)
Automatic attention slicing for low-memory systems
Seed control for reproducible generations
Multi-LoRA support with adjustable strengths

InstallMCPRun via uvx (Python)

Universal installANY TOOL

$ npx skillcity@latest iconben/z-image-studio

Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.

Requires Node.js 18+ (ships with npx).

Or install manually

uvx z-image-studio

MCP Configuration

Add this to your claude_desktop_config.json

{
  "mcpServers": {
    "z-image-studio": {
      "command": "uvx",
      "args": [
        "z-image-studio"
      ]
    }
  }
}

Loading README…

Discover the toolingbehind modern intelligence

Discover the toolingbehind modern intelligence

z-image-studio