import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Felldude/stable-diffusion-v1-5-248-CLIP", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]100k Iterations training both the attention and UNET to use 248 CLIP from HiDream
- Downloads last month
- 43
Model tree for Felldude/stable-diffusion-v1-5-248-CLIP
Base model
stable-diffusion-v1-5/stable-diffusion-v1-5