Back to directory

Z-Image Turbo - One-Click Windows Installer (Low VRAM)

A one-click Windows installer that sets up a local Z-Image Turbo image-generation model behind a Gradio web interface, tuned for GPUs with as little as 4 GB of VRAM.

Z-Image Turbo - One-Click Windows Installer (Low VRAM)

This project packages the Z-Image Turbo GGUF image-generation model as a one-click Windows installer with a Gradio web interface, aimed at users with low-VRAM NVIDIA GPUs, including cards with only 4 GB, who want to run local image generation without configuring the underlying tools by hand. A first-run setup wizard detects the machine's hardware, recommends a matching profile, creates an isolated Python virtual environment, and downloads the required model weights, VAE, and text encoder automatically.

The web interface exposes prompt, resolution, seed, and CFG controls, a background generation queue that accepts new prompts while another image is still generating, and a status table showing running, queued, done, failed, and stopped states. It also includes experimental image-to-image and inpainting modes built on stable-diffusion.cpp, and LoRA support through a local model folder.

It requires Windows 10 or 11, Python 3.10 or newer, and the Microsoft Visual C++ Redistributable, with an NVIDIA GPU as optional but recommended.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.