LivePortrait：一张照片生成生动视频，精准操控眼睛和嘴唇动作 本地一键整合包下载
LivePortrait，这个名字听起来就像是魔法，但它其实是现实世界中的黑科技。想象一下，你那尘封已久的相册里，那些定格在时间里的笑脸，突然间动了起来，眨眼、微笑、甚至说话，这不再是电影里的场景，LivePortrait让它变成了现实。这是由业界大厂快手开源的一个项目，前段时间可灵的爆火，也让快手跟着火了一把，这个项目的开源，让老厂再次焕发新颜。这个框架，就像是一个神奇的画笔，只需要你提供一张静态的肖像，它就能绘制出一段流畅的动态视频。这不仅仅是技术上的突破，更是对传统动画制作的一次颠覆。它高效、精确，甚至还能处理多人物肖像的无缝拼接，让每个人物的动作都自然流畅，没有任何突兀的边界。
https://pic.imgdb.cn/item/66880b2cd9c307b7e97a917f.gif
https://pic.imgdb.cn/item/66880cb0d9c307b7e97dd031.gif
https://pic.imgdb.cn/item/66880db1d9c307b7e97fe339.gif
需求人群："目标受众包括动画制作者、游戏开发者、电影后期制作人员等，他们需要快速生成逼真的人像动画，用于角色设计、广告制作或其他视觉媒体项目。LivePortrait因其高效和可控性，特别适合需要快速迭代和精确控制动画细节的专业用户。"
使用场景示例：动画制作者使用LivePortrait快速生成角色动画，用于动画电影的预览。游戏开发者利用LivePortrait为游戏角色创建逼真的面部表情。广告制作团队使用LivePortrait为产品广告生成吸引人的动态人像。
产品特色：从静态图像生成不同风格（现实、油画、雕塑、3D渲染）的人像动画通过Kling生成的源视频进行人像视频编辑基于给定的标量控制眼睛和嘴唇的开合程度通过微调动物数据，实现对猫、狗和熊猫的精确驱动在RTX 4090 GPU上以PyTorch实现12.8ms的生成速度
现在，无论你是想制作一段个性化的肖像视频，还是想给老照片赋予新的生命，LivePortrait都能帮你轻松实现。这不仅仅是一个工具，更是一个让创意无限扩展的平台。所以，别再让你的照片沉睡在相册里了，让LivePortrait唤醒它们，让它们动起来，讲述属于它们自己的故事。
使用教程：（只支持N卡，显存8G起）
解压本地一键整合包，双击一键启动
上传一张需要生成的图片，即源图像和驱动视频，驱动视频即参考做表情动作的视频
可以根据页面提示，手动调整参数，然后点“生成动画”即可
稍等片刻，速度还是很快的，即可看到按照参考视频生成后的动画视频。
注意事项：1、驱动视频建议将其裁剪为1:1 的宽高比（例如 512x512 或 256x256 像素），或通过 启用自动裁剪；2、驱动视频关注头部区域，建议与示例视频类似；3、驱动视频尽量减少肩部运动；4、驱动视频第一帧是正面且表情中性；5、原图像尽量使用大头照，且面部清晰
下载地址：（下载前，请先阅读 使用说明 再下载，避免不必要的问题和纠纷）**** 本内容需购买 **** 这个项目适合自媒体，比如打造一个读书类或者科普类的数字人账号
也可以用于接单，比如做ai亲人复活类项目，只要你懂运营，分分钟打造一个火爆的IP 大佬手上都是极好的资源，感谢分享！ 点一键启动进去就这样
-----------------------------------------------
更多好玩的AI应用，访问 https://deepface.cc
LivePortrait WebUI正在启动中，请稍后
-----------------------------------------------
D:\LivePortrait\python\lib\site-packages\torch\cuda\__init__.py:184: UserWarning:
Found GPU0 GeForce GTX 650 which is of cuda capability 3.0.
PyTorch no longer supports this GPU because it is too old.
The minimum cuda capability supported by this library is 3.7.
warnings.warn(
Load appearance_feature_extractor done. live_portrait_wrapper.py:29
Load motion_extractor done. live_portrait_wrapper.py:32
Load warping_module done. live_portrait_wrapper.py:35
Traceback (most recent call last):
File "D:\LivePortrait\app.py", line 28, in <module>
gradio_pipeline = GradioPipeline(
File "D:\LivePortrait\src\gradio_pipeline.py", line 26, in __init__
super().__init__(inference_cfg, crop_cfg)
File "D:\LivePortrait\src\live_portrait_pipeline.py", line 38, in __init__
self.live_portrait_wrapper: LivePortraitWrapper = LivePortraitWrapper(cfg=inference_cfg)
File "D:\LivePortrait\src\live_portrait_wrapper.py", line 37, in __init__
self.spade_generator = load_model(cfg.checkpoint_G, model_config, cfg.device_id, 'spade_generator')
File "D:\LivePortrait\src\utils\helper.py", line 103, in load_model
model = SPADEDecoder(**model_params).cuda(device)
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 915, in cuda
return self._apply(lambda t: t.cuda(device))
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 779, in _apply
module._apply(fn)
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 779, in _apply
module._apply(fn)
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 779, in _apply
module._apply(fn)
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 804, in _apply
param_applied = fn(param)
File "D:\LivePortrait\python\lib\site-packages\torch\nn\modules\module.py", line 915, in <lambda>
return self._apply(lambda t: t.cuda(device))
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU
请按任意键继续. . . 生成就卡主了。半个小时没有反应，视频也不大十秒左右下面显示错误
哈哈哈雷 发表于 2024-7-23 18:51
生成就卡主了。半个小时没有反应，视频也不大十秒左右下面显示错误
贴上黑色窗口错误信息 哈哈哈雷 发表于 2024-7-23 18:51
生成就卡主了。半个小时没有反应，视频也不大十秒左右下面显示错误
哈哈哈雷 发表于 2024-7-23 19:19
复制粘贴会吗？ To create a public link, set `share=True` in `launch()`.
[ WARN:[email protected]] global loadsave.cpp:241 cv::findDecoder imread_('C:\Users\Administrator\AppData\Local\Temp\gradio\92bd4746f73e1bc029d66cbd0964915c820bf430\12333333_鍓湰.jpeg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
File "D:\live\LivePortrait\python\lib\site-packages\gradio\queueing.py", line 541, in process_events
response = await route_utils.call_process_api(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\route_utils.py", line 276, in call_process_api
output = await app.get_blocks().process_api(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\blocks.py", line 1928, in process_api
result = await self.call_function(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\blocks.py", line 1514, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\live\LivePortrait\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "D:\live\LivePortrait\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread
return await future
File "D:\live\LivePortrait\python\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run
result = context.run(func, *args)
File "D:\live\LivePortrait\python\lib\site-packages\gradio\utils.py", line 833, in wrapper
response = f(*args, **kwargs)
File "D:\live\LivePortrait\src\gradio_pipeline.py", line 111, in prepare_retargeting
img_rgb = load_img_online(input_image_path, mode='rgb', max_dim=1280, n=16)
File "D:\live\LivePortrait\src\utils\io.py", line 90, in load_img_online
img = resize_to_limit(img, max_dim=max_dim, n=n)
File "D:\live\LivePortrait\src\utils\io.py", line 51, in resize_to_limit
h, w = img.shape[:2]
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:241 cv::findDecoder imread_('C:\Users\Administrator\AppData\Local\Temp\gradio\92bd4746f73e1bc029d66cbd0964915c820bf430\12333333_鍓湰.jpeg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
File "D:\live\LivePortrait\python\lib\site-packages\gradio\queueing.py", line 541, in process_events
response = await route_utils.call_process_api(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\route_utils.py", line 276, in call_process_api
output = await app.get_blocks().process_api(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\blocks.py", line 1928, in process_api
result = await self.call_function(
File "D:\live\LivePortrait\python\lib\site-packages\gradio\blocks.py", line 1514, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\live\LivePortrait\python\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "D:\live\LivePortrait\python\lib\site-packages\anyio\_backends\_asyncio.py", line 2177, in run_sync_in_worker_thread
return await future
File "D:\live\LivePortrait\python\lib\site-packages\anyio\_backends\_asyncio.py", line 859, in run
result = context.run(func, *args)
File "D:\live\LivePortrait\python\lib\site-packages\gradio\utils.py", line 833, in wrapper
response = f(*args, **kwargs)
File "D:\live\LivePortrait\src\gradio_pipeline.py", line 63, in execute_video
video_path, video_path_concat = self.execute(self.args)
File "D:\live\LivePortrait\src\live_portrait_pipeline.py", line 44, in execute
img_rgb = load_image_rgb(args.source_image)
File "D:\live\LivePortrait\src\utils\io.py", line 15, in load_image_rgb
return cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'
哈哈哈雷 发表于 2024-7-23 19:40
To create a public link, set `share=True` in `launch()`.
[ WARN:[email protected]] global loadsave.cpp:241 cv ...
图片文件名不要有中文，任何文件名都不要有中文
页:
[1]
2