by leejet
Open source · 24k downloads · 37 likes
Z Image Turbo GGUF is an AI model optimized for generating images from text, designed to run efficiently even on modest hardware configurations. Thanks to its quantized files, it produces high-quality visuals while minimizing memory requirements, making it ideal for users with graphics cards limited to 4GB of VRAM. Its key features include fast generation of diverse images with strong adherence to provided prompts, all while remaining accessible and easy to deploy. This model stands out for its balance between performance and lightweight design, offering a practical solution for creators, developers, or artists looking to integrate local image generation without relying on costly cloud resources. Its quantized approach makes it particularly well-suited for environments where energy efficiency and speed are critical.
The license of the quantized files follows the license of the original model:
These files are converted using https://github.com/leejet/stable-diffusion.cpp
You can use these weights with stable-diffusion.cpp to generate images.
.\bin\Release\sd.exe --diffusion-model z_image_turbo-Q3_K.gguf --vae ae.safetensors --llm Qwen3-4B-Instruct-2507-Q4_K_M.gguf -p "A cinematic, melancholic photograph of a solitary hooded figure walking through a sprawling, rain-slicked metropolis at night. The city lights are a chaotic blur of neon orange and cool blue, reflecting on the wet asphalt. The scene evokes a sense of being a single component in a vast machine. Superimposed over the image in a sleek, modern, slightly glitched font is the philosophical quote: 'THE CITY IS A CIRCUIT BOARD, AND I AM A BROKEN TRANSISTOR.' -- moody, atmospheric, profound, dark academic" --cfg-scale 1.0 -v --offload-to-cpu --diffusion-fa -H 1024 -W 512
| bf16 | q8_0 | q6_K | q5_0 | q4_K | q4_0 | q3_K | q2_K |
|---|---|---|---|---|---|---|---|
![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() | ![]() |