How to use DongKyung/Imagic with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DongKyung/Imagic", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
This is Just for U-NET fine-tuning in Imagic
No Other Use
But, if you want Imagic
You can refer to 'Imagic_medium.ipynb'
You should read every singgle comment in this .ipynb
then, you can create own your Imagic Model
Have fun!!
