Z-Image Turbo on HuggingFace

Z-Image Turbo model on HuggingFace platform, with over 110k monthly downloads

HuggingFace

Community

Model

110k+ Downloads

Overview

Z-Image Turbo model in HuggingFace community, providing complete model weights, usage examples and community support. Monthly downloads reach 111,244.

Features

Community discussion and feedback
Model weight downloads
Detailed usage examples
Decoupled-DMD acceleration algorithm
DMDR: DMD combined with reinforcement learning

Images

Z-Image performance ranking on AI Arena

Installation

pip install -U huggingface_hub
HF_XET_HIGH_PERFORMANCE=1 hf download Tongyi-MAI/Z-Image-Turbo

Usage

import torch
from diffusers import ZImagePipeline

pipe = ZImagePipeline.from_pretrained(
    "Tongyi-MAI/Z-Image-Turbo",
    torch_dtype=torch.bfloat16,
)
pipe.to("cuda")
image = pipe(prompt="your prompt", num_inference_steps=9, guidance_scale=0.0).images[0]

Requirements

Python 3.8+
PyTorch
Diffusers (install from source)
CUDA compatible GPU