Tune-A-VideKO-v1-5 / README.md
kyujinpy's picture
Upload README.md
e63b9dc
metadata
license: creativeml-openrail-m
base_model: Bingsu/my-korean-stable-diffusion-v1-5
training_prompt: A man is surfing
tags:
  - tune-a-video
  - text-to-video
  - diffusers
  - korean
inference: false

Tune-A-VideKO - Korean Stable Diffusion v1-5

Github: Kyujinpy/Tune-A-VideKO

Model Description

Samples

sample-500 Test prompt: λ―Έν‚€λ§ˆμš°μŠ€κ°€ μ„œν•‘μ„ 타고 μžˆμŠ΅λ‹ˆλ‹€

sample-500 Test prompt: ν•œ μ—¬μžκ°€ μ„œν•‘μ„ 타고 μžˆμŠ΅λ‹ˆλ‹€

sample-500 Test prompt: 흰색 μ˜·μ„ μž…μ€ λ‚¨μžκ°€ λ°”λ‹€λ₯Ό κ±·κ³  μžˆμŠ΅λ‹ˆλ‹€

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 = "Bingsu/my-korean-stable-diffusion-v1-5"
unet_model_path = "kyujinpy/Tune-A-VideKO-v1-5"
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 = "흰색 μ˜·μ„ μž…μ€ λ‚¨μžκ°€ λ°”λ‹€λ₯Ό κ±·κ³  μžˆμŠ΅λ‹ˆλ‹€"
video = pipe(prompt, video_length=24, height=512, width=512, num_inference_steps=50, guidance_scale=12.5).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