Instructions to use xcreates/Z-Image-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xcreates/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("xcreates/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
- Draw Things
- DiffusionBee
Upload complete model
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ library_name: diffusers
|
|
| 10 |
## Usage Notes
|
| 11 |
|
| 12 |
#### Tested using [xCreate app](https://xcreate.com)
|
|
|
|
| 13 |
* M4 Max: ~50 seconds per generation
|
| 14 |
* M1 Max: ~125 seconds per generation
|
| 15 |
* Memory usage: ~30 GB
|
|
|
|
| 10 |
## Usage Notes
|
| 11 |
|
| 12 |
#### Tested using [xCreate app](https://xcreate.com)
|
| 13 |
+
* M3 Ultra: ~34 seconds per generation
|
| 14 |
* M4 Max: ~50 seconds per generation
|
| 15 |
* M1 Max: ~125 seconds per generation
|
| 16 |
* Memory usage: ~30 GB
|