Tune-A-VideKO-anything

Github: Kyujinpy/Tune-A-VideKO

Model Description

• Base model: kyujinpy/KO-anything-v4-5
• Training prompt: A bear is playing guitar

Samples

Test prompt: 1소녀는 기타를 연주하고 있다, 흰 머리, 중간 머리, 고양이 귀, 귀여운, 스카프, 재킷, 야외, 거리, 소녀

Test prompt: 1소녀가 기타 연주를 하고 있습니다, 바다, 눈을 감음, 긴 머리, 카리스마

Test prompt: 1소년, 기타 연주, 잘생김, 앉아있는, 빨간색 기타, 해변

Usage

Clone the github repo

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

Run inference code

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")

Related Papers:

• Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
• Stable Diffusion: High-Resolution Image Synthesis with Latent Diffusion Models