import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("glowforge-prod/stable-diffusion-2-1-custom", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Stable Diffusion v2-1 Custom Implementation
Custom implementation of the Stable Diffusion v2.1 base model for Glowforge.
Forked from the Stable Diffusion v2.1 base model developed by Robin Rombach and Patrick Esser.
- Downloads last month
- 64