Instructions to use Ttio2/Z-Image-Turbo-Ghibli-Style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ttio2/Z-Image-Turbo-Ghibli-Style 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") pipe.load_lora_weights("Ttio2/Z-Image-Turbo-Ghibli-Style") prompt = "an image of a young woman sitting outdoors on grass. She appears to be in her 20s with brown hair tied back in a ponytail. She is wearing a dark blue sports bra-style crop top that shows her midriff, paired with high-waisted olive green cargo pants. She has a white shirt or jacket draped over her shoulders. Around her neck is a silver chain necklace, and she is wearing small hoop earrings. " image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Is it possible to retrain a new LoRA using z‑image‑base?
#1 opened 4 months ago
by
makisekurisu-jp