import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("envvi/inkpunk-diffusion", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ephmecx/vinpo-inkpunk")
prompt = "a photo in vinpo style"
image = pipe(prompt).images[0]LoRA DreamBooth - ephmecx/vinpo-inkpunk
These are LoRA adaption weights for envvi/inkpunk-diffusion. The weights were trained on a photo in vinpo style using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
- Downloads last month
- 4