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 Settings
- Draw Things
- DiffusionBee
Impressive small model and most uncensored too
#50
by Flanua - opened
Partially even offloaded BF16 variant to GTX 980Ti 6GB GPU and it only take 1 min 50 sec to generate a picture with this GPU cus it cant fit a whole model in Vram. Very fast and impressive! Also this model the most uncensored model too and can even generate genitalia for girls of all ages. That being said its one of the best text to Image model (considering limited amount of data it was trained on) that I ever tried and I tried many. Thank you for this awesome AI model it would help a lot.
Flanua changed discussion title from Impressive small model and most uncensored too. to Impressive small model and most uncensored too
π€«
QJerry changed discussion status to closed