import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-T2V-A14B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("punzel/wan_sydney_sweeney")
prompt = "-"
image = pipe(prompt).images[0]Sydney Sweeney
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
Testing out Wan 2.2, trained on 18 images of Sydney Sweeney for 1800 steps. This includes a high and low model. All images were generated in 30 steps using 15 steps for the high lora and 15 steps for the low lora.
trigger: wansyd
helpers: young woman with long wavy blonde hair, blue eyes, fair skin, and subtle makeup
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 115
Model tree for punzel/wan_sydney_sweeney
Base model
Wan-AI/Wan2.2-T2V-A14B