How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("rupeshs/sdxs-512-0.9-orig-vae", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

This is same as original model IDKiro/sdxs-512-0.9 only difference is this model uses original VAE (Improves image quality)

Downloads last month
183
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Spaces using rupeshs/sdxs-512-0.9-orig-vae 2