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
Request: Could you release the FP32 version of the Transformer?
#10
by easygoing0114 - opened
Hi there.
Thank you for releasing this amazing model!
I am interested in creating a derivative model based on Z-Image. Would it be possible to release the Transformer in FP32 format, similar to what was done for Z-Image-Turbo?
Since this model is lightweight, I would like to aim for the highest possible image quality in a local environment.
Thank you for your consideration!
You can get if from the first commit!
https://huggingface.co/Tongyi-MAI/Z-Image/tree/1ac663bf5fcfa5b4752f9e1315cbb5a4541ed7b8
Greatly helpful, thank you!