import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SargeZT/velocipedeux", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Card for Velocipedeux
A Stable Diffusion 1.5 model finetuned with v-prediction, zero terminal SNR, and trailing timesteps using a diverse dataset.
Model Details
Model Description
This model is a finetune of Stable Diffusion 1.5 that implements Zero Terminal SNR scaling, V-Prediction, and the use of trailing timesteps during training.
This model is in active development and should not be considered final.
- Downloads last month
- 6