import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ilkerc/openjourney-v2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This repo is for testing the first Openjourney fine tuned model.
It was trained over Stable Diffusion 1.5 with +60000 images, 4500 steps and 3 epochs.
So "mdjrny-v4 style" is not necessary anymore (yay!)
Things to check in this beta:
- Is the quality better that the Dreambooth version?
- Downloads last month
- 2