NVIDIA Cosmos 3: 물리 AI 추론 및 행동을 위한 최초의 오픈 옴니 모델

import torch
from diffusers import Cosmos3OmniPipeline

pipe = Cosmos3OmniPipeline.from_pretrained(
    "nvidia/Cosmos3-Nano",
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)

prompt = (
    "A medium shot of a modern robotics research laboratory with white walls and a gray floor. "
    "A robotic arm with a metallic finish is mounted on a clean white workbench, its gripper positioned "
    "above a row of small colored objects. A laptop and neatly arranged tools sit beside the robot. "
    "A large monitor on the wall behind displays a software interface. The scene is brightly lit by "
    "overhead fluorescent lights."
)

result = pipe(prompt=prompt, num_frames=1, height=720, width=1280)
result.video[0].save("cosmos3_t2i.jpg", format="JPEG", quality=85)