Tune A VideKO Disney

🚀 Tune-A-VideKO-anything

Tune-A-VideKO-anything是一个基于特定基础模型训练的文本到视频生成模型，能依据输入的文本生成具有现代迪士尼风格的视频，可应用于创意视频制作等场景。

🚀 快速开始

克隆代码仓库

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

运行推理代码

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-stable-diffusion-disney"
unet_model_path = "kyujinpy/Tune-A-VideKO-disney"
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 = "사자가 기타를 치고 있습니다, 모던한 디즈니 스타일"
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")

✨ 主要特性

• 特定基础模型：基于 kyujinpy/KO-stable-diffusion-disney 模型进行训练。
• 特定训练提示：使用 “A bear is playing guitar” 进行训练。
• 多场景生成：能根据不同的测试提示，如兔子、王子、狮子弹吉他等，生成具有现代迪士尼风格的视频。

📦 安装指南

克隆项目代码仓库：

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

💻 使用示例

基础用法

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-stable-diffusion-disney"
unet_model_path = "kyujinpy/Tune-A-VideKO-disney"
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 = "사자가 기타를 치고 있습니다, 모던한 디즈니 스타일"
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")

📚 详细文档

模型描述

• 基础模型：kyujinpy/KO-stable-diffusion-disney
• 训练提示：A bear is playing guitar

示例展示

测试提示：토끼가 기타를 치고 있습니다, 모던한 디즈니 스타일

测试提示：잘생긴 왕자가 기타를 치고 있습니다, 모던한 디즈니 스타일

测试提示：사자가 기타를 치고 있습니다, 모던한 디즈니 스타일

相关论文

• 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

📄 许可证

本模型使用的许可证为 creativeml-openrail-m。

Github链接：Kyujinpy/Tune-A-VideKO