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("OlafII/cosmosx", dtype=torch.bfloat16, device_map="cuda")

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

Cosmosx is a fine tuned Stable Diffusion model trained on high quality star constellation images

Use in prompt: "cosmosx"
Trained on Stable Diffusion v1.5 using ShivamShrirao Dreambooth

Cosmosx Rendered:

Steps: 35, Default Automatic1111 settings

Training Info

Trained on 12 images with 2000 Steps

Downloads last month
17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support