Instructions to use ostris/zimage_turbo_training_adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/zimage_turbo_training_adapter 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("ostris/zimage_turbo_training_adapter") 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
Character Lora Training under 12GB VRAM - under 1hr on 5070 ti
👍 2
#6 opened 5 months ago
by
TheOCroc
Negative alpha as distill accelerate LoRA!
2
#5 opened 6 months ago
by
TkskKurumi
Does Z-Image support embedding/textual-inversion–style adapters? If not, why?
👀 1
#3 opened 6 months ago
by
PlayAI
[Question] Why Training Adapter
7
#1 opened 6 months ago
by
evilperson068