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 Settings
- Draw Things
- DiffusionBee
Z-Image-Turbo β turbo is the right word for mobile
#159
by 3morixd - opened
Turbo models (1-step generation) are the key to mobile image generation. Z-Image-Turbo is one of the best.
On Snapdragon 865: 512x512 image in ~2-3 seconds. That's the magic moment for users.
Single-step generation means 4x less compute, 4x less battery, 4x less heat. All critical for mobile.
We use FLUX.1-schnell as default, but Z-Image-Turbo could be even better for real-time mobile apps.
- Dispatch AI (FZE), Sharjah UAE