Instructions to use Tongyi-MAI/Z-Image-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Tongyi-MAI/Z-Image-Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
z-image models is specially only working with qwen3 4b ?
any other qwen3 version can be used ? if not , then why ? technically ..
Hi, thanks for your interest in our work.
Our model is trained with qwen3-4b, so yes, our diffusion model works exclusively with qwen3-4b.
By the way, I am really curious why you would think it useful / meaningful if you could replace qwen-3 4b with other language backbones 😂 If possible, could you explain why there is such a demand?
qwen3-8B是不是更好一些呢,语义理解方面
Hi, thanks for your interest in our work.
Our model is trained with qwen3-4b, so yes, our diffusion model works exclusively with qwen3-4b.
By the way, I am really curious why you would think it useful / meaningful if you could replace qwen-3 4b with other language backbones 😂 If possible, could you explain why there is such a demand?
It seems Qwen3-4B 2507 series are better than original ones