import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Disty0/sd3_randn_aura_vae", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]An anime model trained on randomly initialized SD3 Transformer weights with RMSNorm and AuraDiffusion 16ch VAE.
Trained on 256px resolutions using anime dataset.
Requires Diffusers with RMSNorm support: https://github.com/Disty0/diffusers/tree/sd3_rms_norm
- Downloads last month
- 6