Instructions to use ostris/Z-Image-De-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/Z-Image-De-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("ostris/Z-Image-De-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
- Draw Things
- DiffusionBee
I cant wait!
#1
by Kutches - opened
Also does this model converge the same as turbo or it needs more steps asking to use for inference.
I am still testing training on top of it. It should behave like training with the training adapter, as the fine tune started with a merge in of that adapter, but it has been fully fine tuned so it will hopefully work better than the adapter.
ooh I am will try it thanks for all the work :)
how can I try to teach using this model? I really want to try it.
Any example workflows yet?