GenshinImpact_XL_Base

svjack/GenshinImpact_XL_Base

This model is derived from CivitAI.

Acknowledgments

Special thanks to mobeimunan for their contributions to the development of this model.

<!-- from moviepy.editor import ImageClip, VideoFileClip, concatenate_videoclips, clips_array # 定义图像和视频的路径 image1_path = "https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/3IkZz7uXW9kc-lTnKdQN8.png" image2_path = "https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/ckrKqytF5MhanjIc_Vn1q.png" image3_path = "https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/vfffGerUQV9W1MHxc_rN_.png" video_path = "https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/gBaodBk8z3aI69LiT36w2.mp4" duration = 10 # 加载图像和视频 image1 = ImageClip(image1_path).set_duration(duration).resize(height = 512, width = 512) # 设置图像的持续时间为10秒 image2 = ImageClip(image2_path).set_duration(duration).resize(height = 512, width = 1024) image3 = ImageClip(image3_path).set_duration(duration).resize(height = 512, width = 1024) video = VideoFileClip(video_path).resize(height = 512, width = 512) # 调整视频的持续时间以匹配图像 video = video.subclip(0, duration) # 截取视频的前10秒 # 将图像和视频拼接成一个2x2的网格 final_clip = clips_array([[image1, image2], [video, image3]]) # 调整最终视频的宽高比 final_clip = final_clip.resize(width=1080) # 调整宽度为1080，高度会自动调整 # 导出最终视频 final_clip.write_videofile("zhongli_merge_im_output.mp4", codec="libx264") VideoFileClip("zhongli_merge_im_output.mp4").set_duration(2.2).write_videofile("zhongli_merge_output_2_2.mp4", codec="libx264") --> <div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/bsgBrDOOXYN-oBH95q5uK.mp4" style="width: 1024px; height: 768x;"></video> </div> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/WypE04ag7_4Z1FKhzk475.png" width="1024" height="1024"> </div> <div style="margin-bottom: 10px;"> <h3>Zhongli Drinking Tea:</h3> </div> <div style="margin-bottom: 10px;"> <img src="https://github.com/user-attachments/assets/00451728-f2d5-4009-afa8-23baaabdc223" style="width: 1024px; height: 256px;"> </div> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://github.com/user-attachments/assets/607e7eb7-d41c-4740-9c8a-8369c31487da" style="width: 1024px; height: 800px;"></video> </div> <div style="margin-bottom: 10px;"> <h3>Kamisato Ayato Smiling:</h3> </div> <div style="margin-bottom: 10px;"> <img src="https://github.com/user-attachments/assets/7a920f4c-8a3a-4387-98d6-381a798566ef" style="width: 1024px; height: 256px;"> </div> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://github.com/user-attachments/assets/aaa9849e-0c53-4012-b6c3-9ceb9910f2f8" style="width: 1024px; height: 800px;"></video> </div> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/Kmh4NJ1AkfV5X3-kkilAK.mp4" style="width: 1024px; height: 1024px;"></video> </div> </div>

Supported Characters

The model currently supports the following 73 characters from Genshin Impact:

name_dict = {
    '旅行者女': 'lumine',
    '旅行者男': 'aether',
    '派蒙': 'PAIMON',
    '迪奥娜': 'DIONA',
    '菲米尼': 'FREMINET',
    '甘雨': 'GANYU',
    '凯亚': 'KAEYA',
    '莱依拉': 'LAYLA',
    '罗莎莉亚': 'ROSARIA',
    '七七': 'QIQI',
    '申鹤': 'SHENHE',
    '神里绫华': 'KAMISATO AYAKA',
    '优菈': 'EULA',
    '重云': 'CHONGYUN',
    '夏洛蒂': 'charlotte',
    '莱欧斯利': 'WRIOTHESLEY',
    '艾尔海森': 'ALHAITHAM',
    '柯莱': 'COLLEI',
    '纳西妲': 'NAHIDA',
    '绮良良': 'KIRARA',
    '提纳里': 'TIGHNARI',
    '瑶瑶': 'YAOYAO',
    '珐露珊': 'FARUZAN',
    '枫原万叶': 'KAEDEHARA KAZUHA',
    '琳妮特': 'LYNETTE',
    '流浪者 散兵': 'scaramouche',
    '鹿野院平藏': 'SHIKANOIN HEIZOU',
    '琴': 'JEAN',
    '砂糖': 'SUCROSE',
    '温迪': 'VENTI',
    '魈': 'XIAO',
    '早柚': 'SAYU',
    '安柏': 'AMBER',
    '班尼特': 'BENNETT',
    '迪卢克': 'DILUC',
    '迪西娅': 'DEHYA',
    '胡桃': 'HU TAO',
    '可莉': 'KLEE',
    '林尼': 'LYNEY',
    '托马': 'THOMA',
    '香菱': 'XIANG LING',
    '宵宫': 'YOIMIYA',
    '辛焱': 'XINYAN',
    '烟绯': 'YANFEI',
    '八重神子': 'YAE MIKO',
    '北斗': 'BEIDOU',
    '菲谢尔': 'FISCHL',
    '九条裟罗': 'KUJO SARA',
    '久岐忍': 'KUKI SHINOBU',
    '刻晴': 'KEQING',
    '雷电将军': 'RAIDEN SHOGUN',
    '雷泽': 'RAZOR',
    '丽莎': 'LISA',
    '赛诺': 'CYNO',
    '芙宁娜': 'FURINA',
    '芭芭拉': 'BARBARA',
    '公子 达达利亚': 'TARTAGLIA',
    '坎蒂丝': 'CANDACE',
    '莫娜': 'MONA',
    '妮露': 'NILOU',
    '珊瑚宫心海': 'SANGONOMIYA KOKOMI',
    '神里绫人': 'KAMISATO AYATO',
    '行秋': 'XINGQIU',
    '夜兰': 'YELAN',
    '那维莱特': 'NEUVILLETTE',
    '娜维娅': 'NAVIA',
    '阿贝多': 'ALBEDO',
    '荒泷一斗': 'ARATAKI ITTO',
    '凝光': 'NING GUANG',
    '诺艾尔': 'NOELLE',
    '五郎': 'GOROU',
    '云堇': 'YUN JIN',
    '钟离': 'ZHONGLI'
}

Installation

To use this model, you need to install the following dependencies:

sudo apt-get update && sudo apt-get install git-lfs ffmpeg cbm
pip install -U diffusers transformers sentencepiece peft controlnet-aux moviepy

Example Usage

Generating an Image of Zhongli

Here's an example of how to generate an image of Zhongli using this model:

from diffusers import StableDiffusionXLPipeline
import torch

pipeline = StableDiffusionXLPipeline.from_pretrained(
    "svjack/GenshinImpact_XL_Base",
    torch_dtype=torch.float16
).to("cuda")

prompt = "solo,ZHONGLI\(genshin impact\),1boy,portrait,upper_body,highres,"
negative_prompt = "nsfw,lowres,(bad),text,error,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,extra digits,artistic error,username,scan,[abstract],"
image = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    generator=torch.manual_seed(0),
).images[0]
image
image.save("zhongli_1024x1024.png")

<div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/3IkZz7uXW9kc-lTnKdQN8.png" width="768" height="768"> <p style="text-align: center;">钟离</p> </div> </div>

Using Canny ControlNet to Restore 2D Images from 3D Toy Photos

Here's an example of how to use Canny ControlNet to restore 2D images from 3D toy photos:

Genshin Impact 3D Toys

<div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/YNG9vRqZGvUSxb_UUrLE5.jpeg" width="512" height="768"> <p style="text-align: center;">钟离</p> </div> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/1JfhfFi9qogHwB4M2S54m.jpeg" width="512" height="768"> <p style="text-align: center;">派蒙</p> </div> </div>

from diffusers import AutoPipelineForText2Image, ControlNetModel
from diffusers.utils import load_image
import torch
from PIL import Image
from controlnet_aux import CannyDetector

controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
)

pipeline = AutoPipelineForText2Image.from_pretrained(
    "svjack/GenshinImpact_XL_Base",
    controlnet=controlnet,
    torch_dtype=torch.float16
).to("cuda")
#pipeline.enable_model_cpu_offload()

canny = CannyDetector()
canny(Image.open("zhongli-cb.jpg")).save("zhongli-cb-canny.jpg")
canny_image = load_image(
    "zhongli-cb-canny.jpg"
)

controlnet_conditioning_scale = 0.5
generator = torch.Generator(device="cpu").manual_seed(1)
images = pipeline(
        prompt="solo,ZHONGLI\(genshin impact\),1boy,portrait,highres",
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        image=canny_image,
        num_inference_steps=50,
        guidance_scale=7.0,
        generator=generator,
    ).images
images[0]
images[0].save("zhongli_trans.png")

canny = CannyDetector()
canny(Image.open("paimon-cb-crop.jpg")).save("paimon-cb-canny.jpg")
canny_image = load_image(
    "paimon-cb-canny.jpg"
)

controlnet_conditioning_scale = 0.7
generator = torch.Generator(device="cpu").manual_seed(3)
images = pipeline(
        prompt="solo,PAIMON\(genshin impact\),1girl,portrait,highres, bright, shiny, high detail, anime",
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        image=canny_image,
        num_inference_steps=50,
        guidance_scale=8.0,
        generator=generator,
    ).images
images[0]
images[0].save("paimon_trans.png")

Creating a Grid Image

You can also create a grid image from a list of PIL Image objects:

from PIL import Image

def create_grid_image(image_list, rows, cols, cell_width, cell_height):
    """
    Create a grid image from a list of PIL Image objects.

    :param image_list: A list of PIL Image objects
    :param rows: Number of rows in the grid
    :param cols: Number of columns in the grid
    :param cell_width: Width of each cell in the grid
    :param cell_height: Height of each cell in the grid
    :return: The resulting grid image
    """
    total_width = cols * cell_width
    total_height = rows * cell_height

    grid_image = Image.new('RGB', (total_width, total_height))

    for i, img in enumerate(image_list):
        row = i // cols
        col = i % cols

        img = img.resize((cell_width, cell_height))

        x_offset = col * cell_width
        y_offset = row * cell_height

        grid_image.paste(img, (x_offset, y_offset))

    return grid_image

create_grid_image([Image.open("zhongli-cb.jpg") ,Image.open("zhongli-cb-canny.jpg"), Image.open("zhongli_trans.png")], 1, 3, 512, 768)

create_grid_image([Image.open("paimon-cb-crop.jpg") ,Image.open("paimon-cb-canny.jpg"), Image.open("paimon_trans.png")], 1, 3, 512, 768)

This will create a grid image showing the original, Canny edge detection, and transformed images side by side.

<div> <b><h3 style="text-align: center;">Below image list in : (Genshin Impact Toy/ Canny Image / Gemshin Impact Restore 2D Image)</h3></b> <div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/ckrKqytF5MhanjIc_Vn1q.png" width="1536" height="768"> <p style="text-align: center;">钟离</p> </div> <div style="margin-bottom: 10px;"> <img src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/vfffGerUQV9W1MHxc_rN_.png" width="1536" height="768"> <p style="text-align: center;">派蒙</p> </div> </div> </div>

Generating an Animation of Zhongli

Here's an example of how to generate an animation of Zhongli using the AnimateDiffSDXLPipeline:

import torch
from diffusers.models import MotionAdapter
from diffusers import AnimateDiffSDXLPipeline, DDIMScheduler
from diffusers.utils import export_to_gif

adapter = MotionAdapter.from_pretrained(
    "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", torch_dtype=torch.float16
)

model_id = "svjack/GenshinImpact_XL_Base"
scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)

pipe = AnimateDiffSDXLPipeline.from_pretrained(
    model_id,
    motion_adapter=adapter,
    scheduler=scheduler,
    torch_dtype=torch.float16,
).to("cuda")

# enable memory savings
pipe.enable_vae_slicing()
pipe.enable_vae_tiling()

output = pipe(
    prompt="solo,ZHONGLI\(genshin impact\),1boy,portrait,upper_body,highres, keep eyes forward.",
    negative_prompt="low quality, worst quality",
    num_inference_steps=20,
    guidance_scale=8,
    width=1024,
    height=1024,
    num_frames=16,
    generator=torch.manual_seed(4),
)
frames = output.frames[0]
export_to_gif(frames, "zhongli_animation.gif")

from diffusers.utils import export_to_video
export_to_video(frames, "zhongli_animation.mp4")
from IPython import display
display.Video("zhongli_animation.mp4", width=512, height=512)

Use AutoPipelineForImage2Image to enhance output:

from moviepy.editor import VideoFileClip
from PIL import Image
clip = VideoFileClip("zhongli_animation.mp4")
frames = list(map(Image.fromarray ,clip.iter_frames()))

from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
from diffusers.utils import load_image, make_image_grid
import torch

pipeline_text2image = AutoPipelineForText2Image.from_pretrained(
    "svjack/GenshinImpact_XL_Base",
    torch_dtype=torch.float16
)

# use from_pipe to avoid consuming additional memory when loading a checkpoint
pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_text2image).to("cuda")

from tqdm import tqdm
req = []
for init_image in tqdm(frames):
    prompt = "solo,ZHONGLI\(genshin impact\),1boy,portrait,upper_body,highres, keep eyes forward."
    image = pipeline(prompt, image=init_image, strength=0.8, guidance_scale=10.5).images[0]
    req.append(image)

from diffusers.utils import export_to_video
export_to_video(req, "zhongli_animation_im2im.mp4")
from IPython import display
display.Video("zhongli_animation_im2im.mp4", width=512, height=512)

Enhancing Animation with RIFE

To enhance the animation using RIFE (Real-Time Intermediate Flow Estimation):

git clone https://github.com/svjack/Practical-RIFE && cd Practical-RIFE && pip install -r requirements.txt
python inference_video.py --multi=128 --video=../zhongli_animation_im2im.mp4

from moviepy.editor import VideoFileClip
clip = VideoFileClip("zhongli_animation_im2im_128X_1280fps.mp4")

def speed_change_video(video_clip, speed_factor, output_path):
    if speed_factor == 1:
        # 如果变速因子为1，直接复制原视频
        video_clip.write_videofile(output_path, codec="libx264")
    else:
        # 否则，按变速因子调整视频速度
        new_duration = video_clip.duration / speed_factor
        sped_up_clip = video_clip.speedx(speed_factor)
        sped_up_clip.write_videofile(output_path, codec="libx264")

speed_change_video(clip, 0.05, "zhongli_animation_im2im_128X_1280fps_wrt.mp4")

VideoFileClip("zhongli_animation_im2im_128X_1280fps_wrt.mp4").set_duration(10).write_videofile("zhongli_animation_im2im_128X_1280fps_wrt_10s.mp4", codec="libx264")
from IPython import display
display.Video("zhongli_animation_im2im_128X_1280fps_wrt_10s.mp4", width=512, height=512)

Merging Videos Horizontally

You can merge two videos horizontally using the following function:

from moviepy.editor import VideoFileClip, CompositeVideoClip

def merge_videos_horizontally(video_path1, video_path2, output_video_path):
    clip1 = VideoFileClip(video_path1)
    clip2 = VideoFileClip(video_path2)

    max_duration = max(clip1.duration, clip2.duration)

    if clip1.duration < max_duration:
        clip1 = clip1.loop(duration=max_duration)
    if clip2.duration < max_duration:
        clip2 = clip2.loop(duration=max_duration)

    total_width = clip1.w + clip2.w
    total_height = max(clip1.h, clip2.h)

    final_clip = CompositeVideoClip([
        clip1.set_position(("left", "center")),
        clip2.set_position(("right", "center"))
    ], size=(total_width, total_height))

    final_clip.write_videofile(output_video_path, codec='libx264')

    print(f"Merged video saved to {output_video_path}")

# Example usage
video_path1 = "zhongli_animation.mp4"  # 第一个视频文件路径
video_path2 = "zhongli_animation_im2im_128X_1280fps_wrt_10s.mp4"  # 第二个视频文件路径
output_video_path = "zhongli_inter_video_im2im_compare.mp4"  # 输出视频的路径
merge_videos_horizontally(video_path1, video_path2, output_video_path)

<div> <b><h3 style="text-align: center;">Left is zhongli_animation.mp4 (By AnimateDiffSDXLPipeline), Right is zhongli_animation_im2im_128X_1280fps_wrt_10s.mp4 (By AutoPipelineForImage2Image + Practical-RIFE)</h3></b> <div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/gBaodBk8z3aI69LiT36w2.mp4"></video> <p style="text-align: center;">钟离</p> </div> </div> </div>

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs - ICML 2024

This repository contains the implementation of a cutting-edge text-to-image diffusion model that leverages multimodal large language models (LLMs) for advanced image generation. The project focuses on recaptioning, planning, and generating high-quality images from textual descriptions, showcasing the capabilities of modern AI in creative content production.

Installation

To get started with the project, follow these steps to set up the environment and install the necessary dependencies:

1. Clone the Repository:

   git clone https://github.com/svjack/RPG-DiffusionMaster
   cd RPG-DiffusionMaster
   

2. Create and Activate Conda Environment:

   conda create -n RPG python==3.9
   conda activate RPG
   

3. Install Jupyter Kernel:

   pip install ipykernel
   python -m ipykernel install --user --name RPG --display-name "RPG"
   

4. Install Required Packages:

   pip install -r requirements.txt
   

5. Clone Diffusers Repository:

   git clone https://github.com/huggingface/diffusers
   

Demo

This section provides a quick demonstration of how to use the RegionalDiffusionXLPipeline to generate images based on textual prompts. The example below demonstrates the process of generating an image using a multimodal LLM to split and refine the prompt.

Import Required Modules

from RegionalDiffusion_base import RegionalDiffusionPipeline
from RegionalDiffusion_xl import RegionalDiffusionXLPipeline
from diffusers.schedulers import KarrasDiffusionSchedulers, DPMSolverMultistepScheduler
from mllm import local_llm, GPT4, DeepSeek
import torch

Load the Model and Configure Scheduler

pipe = RegionalDiffusionXLPipeline.from_single_file(
    "https://huggingface.co/svjack/GenshinImpact_XL_Base/blob/main/sdxlBase_v10.safetensors",
    torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
)
pipe.to("cuda")
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True)
pipe.enable_xformers_memory_efficient_attention()

User Input and MLLM Processing

# User input prompt
prompt = 'ZHONGLI(genshin impact) with NING GUANG(genshin impact) in red cheongsam in the bar.'

# Process the prompt using DeepSeek MLLM
para_dict = DeepSeek(prompt)

# Extract parameters for image generation
split_ratio = para_dict['Final split ratio']
regional_prompt = para_dict['Regional Prompt']
negative_prompt = ""  # Optional negative prompt

Generate and Save the Image

images = pipe(
    prompt=regional_prompt,
    split_ratio=split_ratio,  # The ratio of the regional prompt
    batch_size=1,  # Batch size
    base_ratio=0.5,  # The ratio of the base prompt
    base_prompt=prompt,
    num_inference_steps=20,  # Sampling steps
    height=1024,
    negative_prompt=negative_prompt,  # Negative prompt
    width=1024,
    seed=0,  # Random seed
    guidance_scale=7.0
).images[0]

# Save the generated image
images.save("test_zhong_ning.png")

This demo showcases the power of combining text-to-image diffusion with multimodal LLMs to generate high-quality images from complex textual descriptions. The generated image is saved as test_zhong_ning.png.

---

Feel free to explore the repository and experiment with different prompts and configurations to see the full potential of this advanced text-to-image generation model.

MotionCtrl and MasaCtrl: Genshin Impact Character Synthesis

Check https://github.com/svjack/MasaCtrl to view example about Genshin Impact Character Synthesis video by MasaCtrl

• Zhongli Drinking Tea:

  "solo,ZHONGLI(genshin impact),1boy,highres," -> "solo,ZHONGLI drink tea use chinese cup (genshin impact),1boy,highres,"
  

• Kamisato Ayato Smiling:

  "solo,KAMISATO AYATO(genshin impact),1boy,highres," -> "solo,KAMISATO AYATO smiling (genshin impact),1boy,highres,"
  

<div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <h3>Zhongli Drinking Tea:</h3> </div> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://github.com/user-attachments/assets/607e7eb7-d41c-4740-9c8a-8369c31487da" style="width: 1024px; height: 800px;"></video> </div> <div style="margin-bottom: 10px;"> <h3>Kamisato Ayato Smiling:</h3> </div> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://github.com/user-attachments/assets/aaa9849e-0c53-4012-b6c3-9ceb9910f2f8" style="width: 1024px; height: 800px;"></video> </div> </div>

Perturbed-Attention-Guidance with Genshin Impact XL

Here's an example of how to enhance Genshin Impact XL by https://github.com/svjack/Perturbed-Attention-Guidance:

Clone the Repository

Next, clone the repository from Hugging Face:

git clone https://huggingface.co/spaces/svjack/perturbed-attention-guidance-genshin_impact_xl

Navigate to the Repository Directory

Change into the cloned repository directory:

cd perturbed-attention-guidance-genshin_impact_xl

Install Python Requirements

Install the required Python packages using pip:

pip install -r requirements.txt

Run the Application

Finally, run the application:

python app.py

<div> <b><h3 style="text-align: center;">Left Use BreadcrumbsPerturbed-Attention-Guidance , Right Original Genshin Impact XL</h3></b> <b><h4 style="text-align: center;">Left Seems more pretty </h4></b> <div style="display: flex; flex-direction: column; align-items: center;"> <div style="margin-bottom: 10px;"> <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/Kmh4NJ1AkfV5X3-kkilAK.mp4"></video> </div> </div> </div>