import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("HuggingVince/Br3athPl4y_Krea2")
prompt = "a photo of a woman wearing a plastic bag over her head holding the bottom of the bag closed with her own hands, happy horny cheeky smile, consensual breath-play fetish"
image = pipe(prompt).images[0]Br3athPl4y
- Prompt
- a photo of a woman wearing a plastic bag over her head holding the bottom of the bag closed with her own hands, happy horny cheeky smile, consensual breath-play fetish
Model description
a lora for consensual breath-play fetish seems to work well at 1.0 strength i suspect a few of my input images contribute to the occasional mouth being outside the bag i will do a V2 at some point
Trigger words
You should use Just use natual language E.G. a photo of a woman wearing a plastic bag over her head holding the bottom of the bag closed with her own hands to trigger the image generation.
You should use a photo of a woman wearing a plastic bag over her head to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 25