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
fp16 is not working (Z-Image base incompatible with RTX 20 series, RDNA2 and older)
#22
by Dampfinchen - opened
Please look at this issue here: https://github.com/Comfy-Org/ComfyUI/issues/12176
This is a dealbreaker for users of GPUs older than Ampere (Pre RTX 3000-series, as well as pre- RDNA3.)
Many users still use these kind of GPUs without BF16 support, and Z Image Turbo still worked with the fp16 hack ComfyUI uses.
I hope this can be fixed.