import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ericloux/s2000", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]S2000 Dreambooth model trained by ericloux with TheLastBen's fast-DreamBooth notebook
Test the concept via A1111 Colab fast-Colab-A1111
Or you can run your new concept via diffusers Colab Notebook for Inference
This is a model I (over)trained on the VOGELE SUPER 2000-3i paver, with "S2000 bulldozer" as the prompt. Although it's a paver, I get the most cohesive results when using "bulldozer" over "paver".
Sample pictures of this concept:
- Downloads last month
- 36