wan_2_2_5B_woven_fabric_02-lora

Instala las dependencias:

pip install -U diffusers transformers accelerate

Uso para generar vídeo con Diffusers:

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

# Cambia a "mps" para dispositivos Apple
pipe = DiffusionPipeline.from_pretrained(
    "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)
pipe.load_lora_weights("wouterverweirder/wan_2_2_5B_woven_fabric_02-lora")

prompt = "w0v3nf4br1c"
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

Uso para generar una imagen:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
    torch_dtype=torch.bfloat16
).to("cuda")
pipeline.load_lora_weights(
    "wouterverweirder/wan_2_2_5B_woven_fabric_02-lora",
    weight_name="wan_2_2_5B_woven_fabric_02_000004000.safetensors"
)

image = pipeline("w0v3nf4br1c").images[0]
image.save("my_image.png")

Incluye «w0v3nf4br1c» en el prompt para activar el estilo aprendido.