Instructions to use JoPmt/kandinsky-2-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use JoPmt/kandinsky-2-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("JoPmt/kandinsky-2-1", 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
Download tokenizer/tokenizer.json from JoPmt/kandinsky-2-1: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/JoPmt/kandinsky-2-1/resolve/main/tokenizer/tokenizer.json
- Command line
-
hf download hf://JoPmt/kandinsky-2-1/tokenizer/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/JoPmt/kandinsky-2-1/resolve/main/tokenizer/tokenizer.json
17.1 MB
- Xet hash:
- 0abd02c8ae3c446b4b196b4041ef6b8dc3dce7d172091fa5ca5ce17b4eb7d627
- Size of remote file:
- 17.1 MB
- SHA256:
- f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.