Wan 2.2 Loras
Collection
10 items • Updated
How to use neph1/80s_fantasy_movies_wan_2.2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
# 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("neph1/80s_fantasy_movies_wan_2.2")
prompt = "-"
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")My first Wan lora, so expect sub optimal settings. It uses the same dataset as https://huggingface.co/neph1/1980s_Fantasy_Movies_Hunyuan_Video_Lora. Some things work incredibly well, but in some cases Hunyuan wins.
Low noise model is trained for 30 epochs.
High noise model is trained for 20 epochs.
No logic behind it, I just got tired of waiting.
Prompt example: "a woman warrior clad in steel and chain armor. she walks through a mysterious swamp. she looks wary. mist, smoke rising from the ground, she's holding a staff. dead trees, the scene invokes adventure and mystery, the camera follows the woman ahead"
Download them in the Files & versions tab.
Base model
Wan-AI/Wan2.2-T2V-A14B