Instructions to use google/ncsnpp-ffhq-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use google/ncsnpp-ffhq-256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("google/ncsnpp-ffhq-256", 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
ffhq-256 how are the images resized
#3
by j35t3r - opened
Are the hq files 1024x1024 loaded and downscaled to 256x256 within pytorch transform pipeline?
I would like to calculate the FID
j35t3r changed discussion title from ffhq-256 to ffhq-256 how are the images resized