Instructions to use ostris/krea2_turbo_style_reference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/krea2_turbo_style_reference with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ostris/krea2_turbo_style_reference") prompt = "a white yeti with horns reading a book that is titled \"Ostris + Krea2 Style Reference\"" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Comfy Org officially provided support for your model, but did not release the workflow.
#2
by makisekurisu-jp - opened
"but did not release the workflow"
Because there is no need - Its for API node...
