import torch
from diffsynth.utils.data import save_video
from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig


vram_config = {
    "offload_dtype": "disk",
    "offload_device": "disk",
    "onload_dtype": torch.bfloat16,
    "onload_device": "cpu",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = WanVideoPipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="krea/krea-realtime-video", origin_file_pattern="krea-realtime-video-14b.safetensors", **vram_config),
        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", **vram_config),
        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="Wan2.1_VAE.pth", **vram_config),
    ],
    tokenizer_config=ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 2,
)

# Text-to-video
video = pipe(
    prompt="a cat sitting on a boat",
    num_inference_steps=6, num_frames=81,
    seed=0, tiled=True,
    cfg_scale=1,
    sigma_shift=20,
)
save_video(video, "video_krea-realtime-video.mp4", fps=15, quality=5)