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
- Draw Things
- DiffusionBee
comment incorrect?
#56
by SirZQ - opened
This comment has been hidden (marked as Abuse)
SirZQ changed discussion status to closed
SirZQ changed discussion status to open
The actual model has been run 9 times, right?
No, 1 time, 9 steps for denoising 1 image
Sorry — what I meant is exactly what you said. “num_inference_steps = 9” refers to the result in 9 DiT forwards, not the 8 DiT forwards mentioned in the comment. Is that correct?
Also got confused by this comment.
From the progress bar printed by the progam it's clear that the progress has 9 steps.
So is this just a typo or it suggests that one of the steps is unique among the others and does not result in one DiT forward? I don't understand. Can someone explain? Thanks.
Applu, How are you? I'm fine, Thank you! And you?
