Instructions to use unsloth/Z-Image-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use unsloth/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("unsloth/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] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| Z-Image-Turbo is licensed under the Apache License, Version 2.0. | |
| Copyright Alibaba Group. | |
| This repository is an unmodified mirror of Tongyi-MAI/Z-Image-Turbo, republished by Unsloth so that a quantised | |
| checkpoint of this model can source its companion components (VAE, text encoder, tokenizer, | |
| scheduler) from a single org. The weights are byte for byte those of the source repository. | |
| Not an official Tongyi product and not endorsed by Tongyi. | |
| See LICENSE for the full terms, which are the upstream terms and are unchanged. | |