Origami Lora for WanVideo2.1

Trigger words

You should use origami to trigger the video generation.

Using with Diffusers

pip install git+https://github.com/huggingface/diffusers.git

import torch
from diffusers.utils import export_to_video
from diffusers import AutoencoderKLWan, WanPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler

# Available models: Wan-AI/Wan2.1-T2V-14B-Diffusers, Wan-AI/Wan2.1-T2V-1.3B-Diffusers
model_id = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
flow_shift = 5.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.to("cuda")

pipe.load_lora_weights("shauray/Origami_WanLora")

pipe.enable_model_cpu_offload() #for low-vram environments

prompt = "origami style bull charging towards a man"

output = pipe(
    prompt=prompt,
    height=480,
    width=720,
    num_frames=81,
    guidance_scale=5.0,
).frames[0]
export_to_video(output, "output.mp4", fps=16)

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

license: apache-2.0

---

this Lora is not perfect has a little like towards the bottom of every generation cause the dataset had those (I fucked up cleaning those)