How to use wimvanhenden/blade-runner-2049-v1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wimvanhenden/blade-runner-2049-v1", dtype=torch.bfloat16, device_map="cuda") prompt = "bldrnrst" image = pipe(prompt).images[0]
Use bldrnrst as prompt prefix
bldrnrst, a photo of a man with blood on his face
bldrnrst, a photo of a woman with blood on her face
Results:
Sample pictures of training set:
