Diffusers How to use Ching2602/blinkdoggy with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-I2V-A14B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Ching2602/blinkdoggy")
prompt = "The video begins with shot of a woman. The video then jumpcuts to the same woman now having sex in doggystyle position in the same location. From an overhead perspective, she is on all fours with her back facing the camera. A man is positioned behind her, his hands gripping her hips as he penetrates her from behind. The woman's expression changes throughout the scene, showing moments of pleasure and engagement with her partner. Her legs are spread apart with the man in-between her legs. she is looking directly at the camera fully facing it. she looks back at the camera. she looks at the camera throughout the video."
image = pipe(prompt).images[0] 
