import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("umikaze/umiseMixV2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This model is a block-weighted merge of approximately 10-20 model
⚠Currently in V3.　V2 models are deprecated. → https://civitai.com/models/11627/umisemixv3
This model was created based on the concept of simultaneous depiction of background and human figures. Errors in the model and Lora merged in the last update.
- Downloads last month
- 4