import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Comfy-Org/Wan_2.2_ComfyUI_Repackaged", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Hsama/Laila_High_Noise")
prompt = "A cinematic video of Laila smiling and turning her head slightly, beautiful soft lighting, best quality, 4k"
image = pipe(prompt).images[0]Laila High Noise
- Prompt
- A cinematic video of Laila smiling and turning her head slightly, beautiful soft lighting, best quality, 4k
- Negative Prompt
- blurry, low quality, deformed, malformed, poorly drawn, extra limbs, extra fingers, long neck, watermark, text, jpeg artifacts
Model description
High Noise Lora for Laila
Trigger words
You should use Laila to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Hsama/Laila_High_Noise
Base model
Comfy-Org/Wan_2.2_ComfyUI_Repackaged