Instructions to use Tongyi-MAI/Z-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Tongyi-MAI/Z-Image 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", 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
README Typo?
#8
by warshanks - opened
It appears there might be a typo in the README.
https://huggingface.co/Tongyi-MAI/Z-Image#%F0%9F%86%9A-z-image-vs-z-image-turbo
In this table, Z-Image's visual quality is listed as "High" and Z-Image-Turbo's is listed as "Very High". I'm not sure if that was intentional or not.
Thanks!
It's just curious that the smaller model with fewer steps produces higher quality images. I'll close this as it's that way on their Github too.
warshanks changed discussion status to closed
