Film-Noir

Instala las dependencias y carga el LoRA sobre el modelo base Wan2.1 14B T2V:

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(
    "Wan-AI/Wan2.1-T2V-14B",
    dtype=torch.bfloat16,
    device_map="cuda"
)
pipe.load_lora_weights("Remade-AI/Film-Noir")

prompt = "f11m_n01r film noir, black and white video, a man in a dark trench coat and fedora stands under a flickering streetlamp in a deserted alley. Smoke drifts from a cigarette in his hand, and his face is partially obscured by the shadow of his hat. Rain slicks the pavement, reflecting the glow of distant headlights."

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

En ComfyUI, utiliza el flujo modificado de Wan Video Wrapper y conecta un nodo Wan LoRA al modelo base. Para obtener mejores resultados, empieza los prompts con la frase de activación indicada.