import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kumo24/sdxl_nuclear", torch_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 the Stable Diffusion XL UNet fine-tuned on images related to nuclear energy. Code below shows how to use it.
import torch
from diffusers import DiffusionPipeline, UNet2DConditionModel
custom_unet = UNet2DConditionModel.from_pretrained("kumo24/sdxl_nuclear",
torch_dtype=torch.float16,
use_safetensors=True)
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0",
unet=custom_unet,
torch_dtype=torch.float16,
variant="fp16",
use_safetensors=True).to('cuda')
prompt = "A model of the ZETA generator, Britain’s first nuclear fusion experiment"
image = pipe(prompt).images[0]
image
- Downloads last month
- 43
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for kumo24/sdxl_nuclear
Base model
stabilityai/stable-diffusion-xl-base-1.0