Instructions to use nitrosocke/Ghibli-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/Ghibli-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nitrosocke/Ghibli-Diffusion", 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 Settings
- Draw Things
- DiffusionBee
New style fortnite character
#5
by Kanon14715 - opened
Your trained models are indeed masterpices. I want to ask, do you have plan sharing your magic? Including how to process training dataset and how to imply implement training. I would like to prune a style of fortnite character.
I'll let Nitro answer when he gets time if he wants to add something, but he shared this guide the other day, on style training. It could be a good starting point.