How to use shi-labs/versatile-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("shi-labs/versatile-diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "A high tech solarpunk utopia in the Amazon rainforest" image = pipe(prompt).images[0]
What is the easiest way to know the size of the model if you want to download it locally? This seems to be a very big model.
· Sign up or log in to comment
