import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wavymulder/collage-diffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Collage Diffusion
CKPT DOWNLOAD LINK - - - SAFETENSORS DOWNLOAD LINK
This is a dreambooth model trained on collage images.
Use the activation token collage style in your prompt (I recommend at the start)
I have the most fun with this model when I use simple prompts and let the model go crazy. If you want a model that strictly adheres to your prompt, this isn't that.
Trained from 1.5 with VAE.
- Downloads last month
- 184