import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("TheLastBen/Mushroom_Cloud_XL")
prompt = "mushroom cloud"
image = pipe(prompt).images[0]Mushroom Cloud
SDXL LoRA by TheLastBen
Prompts to start with :
spectacular giant nuclear mushroom cloud, william eggleston, (view through a kitchen window:1.1)
Trained using https://github.com/TheLastBen/fast-stable-diffusion SDXL trainer.
ComfyUI seems to give better results than A1111, but that's just me.
Sample pictures:
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
- Downloads last month
- 16
Model tree for TheLastBen/Mushroom_Cloud_XL
Base model
stabilityai/stable-diffusion-xl-base-1.0