import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("LottePeisch/Dreamshaper6-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Dreamshaper 6 (https://huggingface.co/Lykon/DreamShaper) for InvokeAI Users
- Converted the BakedVae version to Diffusers
- Changed the Scheduler to EulerAncestralDiscreteScheduler
- Changed text_encoder/config.json "num_hidden_layers" to 11 (Equivalent of Clip Skip 2 in Auto1111)
- I made this public for InvokeAI users
- Downloads last month
- 10