import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("opendiffusionai/xllsd-alpha1", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
xllsd-alpha1
This is a work-in-progress for a SD1.5 model, with SDXL VAE, and LongCLIP grafted on.
This is not suitable for normal "I want to make a pretty picture" use. This is only shared here as a test dummy to experiment with LongCLIP + SD1.5 inference.
The output is NOT pretty. (but it is at least human comprehensible, unlike the alpha0 version :) )
Sample ComfyUI workflow
A sample config is provide in this area, as XLLSD-diffusers-comfyui.json
- Downloads last month
- 3