Instructions to use pcuenq/k-upscaler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pcuenq/k-upscaler with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pcuenq/k-upscaler", 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
Commit History
-
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (#1)
- Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`. (fa012bd890328fbd3000ecb05d8095518f789431) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>30df2cd
-
Add model_index (without unet)
6dccfd4 -
Add other components from SD pipeline.
bc58b7c -
Add scheduler (discrete Euler for now)
7a08c4d -
Add vae
10b9c27
-
Update README
8c7844f -
Add configuration and weights.
They were just copied from their original location.98fd8fb -
Create README.md
658bc95 -
initial commit
9b87daf