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
- AMD Developer Cloud
- Local Apps Settings
- Draw Things
- DiffusionBee
Detailed architectural diagram for Z-Image-Turbo
#160
by horsten - opened
Thank you to Tongyi-MAI for creating such a groundbreaking and architecturally interesting (at multiple levels) model and making it open source. As part of my own research involving the model I've created a detailed architectural diagram in collaboration with Claude, which can be found on GitHub here: https://github.com/horsten/z-image-turbo-research-notes/blob/main/z-image-turbo-architecture.svg
I've done my best to ensure it is as accurate and complete as possible, while remaining readable, and sharing it here in the hope that others might benefit from this.