How to use jonathang/pprotein-thing with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jonathang/pprotein-thing", dtype=torch.bfloat16, device_map="cuda") prompt = "3d diagram of the solar system in the style of pprotein" image = pipe(prompt).images[0]
The results are amazing! Thanks for sharing the great model.
How many images did you use? Would it be possible for you to share the training data?
· Sign up or log in to comment
