Ashmotv/vect0r_style_wan_v2-lora

Instala las dependencias:

pip install -U diffusers transformers accelerate

Generación de vídeo con Diffusers:

import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
    dtype=torch.bfloat16,
    device_map="cuda"
)
pipe.load_lora_weights("Ashmotv/vect0r_style_wan_v2-lora")
prompt = "Vect0r style"
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

También se muestra este ejemplo para generar una imagen cargando un archivo de pesos concreto:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    'ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16',
    torch_dtype=torch.bfloat16
).to('cuda')
pipeline.load_lora_weights(
    'Ashmotv/vect0r_style_wan_v2-lora',
    weight_name='vect0r_style_wan_v2_low_noise.safetensors'
)
image = pipeline('Vect0r style').images[0]
image.save("my_image.png")