Tune-A-VideKO-anything

Clonar el repositorio de GitHub

git clone https://github.com/showlab/Tune-A-Video.git

Ejecutar el código de inferencia

from tuneavideo.pipelines.pipeline_tuneavideo import TuneAVideoPipeline
from tuneavideo.models.unet import UNet3DConditionModel
from tuneavideo.util import save_videos_grid
import torch

pretrained_model_path = "kyujinpy/KO-anything-v4-5"
unet_model_path = "kyujinpy/Tune-A-VideKO-anything"
unet = UNet3DConditionModel.from_pretrained(unet_model_path, subfolder='unet', torch_dtype=torch.float16).to('cuda')
pipe = TuneAVideoPipeline.from_pretrained(pretrained_model_path, unet=unet, torch_dtype=torch.float16).to("cuda")
pipe.enable_xformers_memory_efficient_attention()

prompt = "1소녀는 기타를 연주하고 있다, 흰 머리, 중간 머리, 고양이 귀, 귀여운, 스카프, 재킷, 야외, 거리, 소녀"
video = pipe(prompt, video_length=14, height=512, width=512, num_inference_steps=50, guidance_scale=7.5).videos

save_videos_grid(video, f"./{prompt}.gif")