Instructions to use kandinsky-community/kandinsky-2-2-prior with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinsky-community/kandinsky-2-2-prior with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-prior", 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
the tokenizer seems to be clip not mclip?
#5 opened over 1 year ago
by
siwusing
A little typo in prompt
#4 opened almost 3 years ago
by
smileijp
Can we finetune this prior in Diffusers?
#3 opened almost 3 years ago
by
lymhust