import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("apurik-parv/abstract-nature-pattern-v1-2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]abstract_nature_pattern_v1.2 Dreambooth model trained by apurik-parv with TheLastBen's fast-DreamBooth notebook
This model is trained with more data but unfortunately it overfits the image. I am not aware of the extent of overfitting some images are good some are really bad. Please leave suggestions in comment.
Inference Prompt: abnapa
The model is trained on 1024x1024 images for a total step of 3000.
- Downloads last month
- 8