Mademon/malik_wan-lora

Instala las dependencias y carga el adaptador sobre el modelo base con Diffusers:

pip install -U diffusers transformers accelerate

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

# Cambia a "mps" para dispositivos Apple
pipe = DiffusionPipeline.from_pretrained(
    "ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)
pipe.load_lora_weights("Mademon/malik_wan-lora")

prompt = "A man with short gray hair plays a red electric guitar."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

La ficha también proporciona este ejemplo para cargar el archivo específico de pesos LoRA:

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(
    "Mademon/malik_wan-lora",
    weight_name="malik_wan_low_noise.safetensors"
)
image = pipeline("a beautiful landscape").images[0]
image.save("my_image.png")