import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("sd-dreambooth-library/original-character-cyclps", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Original-Character---Cyclps Dreambooth model trained by alvdansen with TheLastBen's fast-DreamBooth notebook
This character was designed with 1500 steps and 12 images. She is a part of a longer character study being done by Archimedes Institute ( http://archimedes.institute.com ) to create a clearer path for artists interested in training original characters into a dreambooth finetune.
Test the concept via A1111 Colab fast-Colab-A1111
Or you can run your new concept via diffusers Colab Notebook for Inference
Sample pictures of this concept:
cyclps
cyclps.png
.jpg)
- Downloads last month
- 11