import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("plasmo/voxel-ish", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Jak's Voxel-ish Image Pack for Stable Diffusion
Another fantastic image pack brought to you by 143 training images through 8000 training steps, 20% Training text crafted by Jak_TheAI_Artist
Include Prompt trigger: "voxel-ish" to activate.
Tip: add "intricate detail" in prompt to make a semi-realistic image.
UPDATE: Version 1.2 available here
Sample pictures of this concept:
voxel-ish
- Downloads last month
- 84