Instructions to use google/ddpm-church-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use google/ddpm-church-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/ddpm-church-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
This model vs google/ddpm-cifar10-32
#3
by Sergo2020 - opened
Hi,
This model seems to run faster than one trained on CFAR10, but ,judging by the architecture, CFAR10 model is lighter. Furtermore, during DDIM inversion and reconstruction CFAR10 manages to reproduce images better.
What is the diffrence between these models, besides train data and architecture?
Thankyou