How to use phil329/face_lora_sd15 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("phil329/face_lora_sd15") prompt = "A young woman with smile, wearing a purple hat." image = pipe(prompt).images[0]
cool lora. how many steps did this take? any other hyperparameters you would be willing to share?
this issue may help
https://huggingface.co/phil329/face_lora_sd15/discussions/2#66fa46f5da62f9ed2d72b164
· Sign up or log in to comment
