import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("erens/GuiltyGearStriveStyleV3", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]guiltygear Dreambooth model trained by erens with TheLastBen's fast-DreamBooth notebook
Test the concept via A1111 Colab fast-Colab-A1111
The final version
Sample pictures of this concept:
1girl, high quality, Mikasa Ackerman, shingeki no kyojin, red scarf, black eyes, portrait, solo, (detailed face, detailed eyes), looking at viewer, shiny skin, arc system works,
30 steps, 8 CFG
- Downloads last month
- 7