import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SargeZT/t2i-adapter-sdxl-multi", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]T2I_Adapter-SargeZT/t2i-adapter-sdxl-multi
These are T2I-adapter weights trained on stabilityai/stable-diffusion-xl-base-1.0
You can find some example images below.
prompt: ['a cat laying on top of a blanket on a bed']
prompt: ['two elephants are walking in a zoo enclosure']
prompt: ['a variety of items are laid out on a table']
prompt: ['a sandwich and french fries on a tray']
prompt: ['a crowd of people flying kites on a beach']
prompt: ['a man holding a rainbow colored umbrella in front of a crowd']
prompt: ['a man riding skis down a snow covered slope']
prompt: ['a yellow fire hydrant sitting in the middle of a sidewalk']
License
- Downloads last month
- -
Model tree for SargeZT/t2i-adapter-sdxl-multi
Base model
stabilityai/stable-diffusion-xl-base-1.0