Instructions to use aipicasso/cool-japan-diffusion-2-1-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aipicasso/cool-japan-diffusion-2-1-0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("aipicasso/cool-japan-diffusion-2-1-0", 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
How was this created? Dreambooth or Textual Inversion?
#4
by joshdance - opened
Very curious about the best way to make a fine tuned model.
Thank you for your question. I just fine-tune Stable Diffusion v2.1 simply. Not dreambooth. Not TI. However, I cannot talk you about the detail method.
Hint: Latent Diffusion Model repository.