返回模型

说明文档

roop-unleashed

更新日志 • 使用方法 • Wiki

无需训练即可生成图片和视频的无审查深度伪造工具，配备易于使用的图形界面。

Screen

功能特性

跨平台浏览器图形界面
一次性选择多个输入/输出人脸
多种替换模式：首次检测、人脸选择、按性别选择
图片/视频批量处理
使用文本提示或自动遮罩人脸遮挡物
可选的人脸放大/修复功能，支持多种增强器
从不同视频帧预览替换效果
使用网络摄像头的实时伪造摄像头
额外功能标签页，用于剪切视频等操作
设置 - 保存配置以供下次会话使用
主题支持

以及更多功能...

免责声明

本项目仅供技术和学术用途。使用本软件的用户应负责任地使用，并遵守当地法律。如果使用真人面部，建议用户获得相关人员的同意，并在网上发布内容时明确说明这是深度伪造内容。本软件的开发者不对最终用户的行为负责。 请勿将其应用于非法和不道德的场景。

若违反用户所在国家或地区的法律和道德要求，本代码仓库不承担任何责任。

安装

请参阅 wiki。

使用方法

Windows：运行安装程序中的 windows_run.bat。
Linux：python run.py

目前不支持额外的命令行参数，设置应通过用户界面完成。

注意：首次运行此程序时，它会下载大约 2GB 的模型文件。

更新日志

22.04.2024 v3.9.0

错误修复：人脸检测边界框在奇怪角度下数值损坏
重写了遮罩预览功能以适配所有模型
切换遮罩引擎可切换文本交互性
清除目标文件会重置人脸选择下拉菜单
大规模重写替换架构，为 xseg 实现做准备
添加了 DFL Xseg 支持部分人脸遮挡
人脸遮罩仅在检测到人脸时运行
移除了文本遮罩的不必要切换复选框

22.03.2024 v3.6.5

错误修复：安装程序在首次安装时拉取最新更新
错误修复：回归问题，人脸替换中缺少模糊/腐蚀效果
将腐蚀和模糊量暴露到用户界面
手动遮罩也使用相同的数值

20.03.2024 v3.6.3

错误修复：Gradio 滑块更改错误的临时解决方案
错误修复：CSS 样式修复 Gradio 图片高度错误
使人脸替换遮罩偏移与分辨率无关
将偏移遮罩显示为叠加层
更改了遮罩布局

18.03.2024 v3.6.0

更新至 Gradio 4.21.0 - 需要大量底层更改
新的手动遮罩功能（自己绘制遮罩）
额外功能标签页，简化视频剪切/合并
重新添加按性别选择人脸（按需加载，默认关闭）
移除了不必要的激活实时摄像头选项
为预览帧添加时间信息，并更改帧滑块事件以允许更快的更改

10.03.2024 v3.5.5

错误修复：安装程序路径环境变量
错误修复：文件属性
视频处理检查 ffmpeg 是否存在，若未找到则显示警告
移除性别 + 年龄检测以加快处理速度。该选项已从用户界面移除
用 restoreformer++ 替换 restoreformer
实时摄像头重新编码，与虚拟摄像头分开运行，不阻塞控件
仅使用 1 个目标人脸进行替换时，可从多个输入人脸上选择

08.01.2024 v3.5.0

错误修复：创建文件夹时访问选项错误
新增水平人脸自动旋转功能，修复错误的标记点位置（扩展自）
简单的 VR 选项，用于立体图片/电影，最适合在选择人脸模式下使用
添加了 RestoreFormer 增强器 - https://github.com/wzhouxiff/RestoreFormer
升级了 onnx/Torch 等包的版本

16.10.2023 v3.3.4

11.8.2023 v2.7.0

初始 Gradio 版本 - 旧的 TkInter 版本现已弃用

重新为人脸增强器添加统一填充
修复 DMDNet 以支持所有分辨率
选择目标人脸现在自动将替换模式切换为已选择
GPU 提供程序可通过用户界面正确设置（目前需要重启）
可从页面打开本地输出文件夹
暂时禁用未完成的额外功能
安装程序检出特定提交，允许回退到首次安装
更新了新版 Gradio 的自述文件
更新了 Colab

致谢

借鉴了以下项目的许多想法、代码或预训练模型：

https://github.com/deepinsight/insightface https://github.com/s0md3v/roop https://github.com/AUTOMATIC1111/stable-diffusion-webui https://github.com/Hillobar/Rope https://github.com/TencentARC/GFPGAN 
https://github.com/kadirnar/codeformer-pip https://github.com/csxmli2016/DMDNet https://github.com/glucauze/sd-webui-faceswaplab https://github.com/ykk648/face_power

感谢所有开发者！

codingggasdfasf/video-animator

作者 codingggasdfasf

diffusers

↓ 0 ♥ 1

创建时间: 2024-05-28 07:22:16+00:00

更新时间: 2024-06-04 09:05:42+00:00

在 Hugging Face 上查看

文件 (339)

.gitattributes

Colab_demo.ipynb

LICENSE

Practical-RIFE/Colab_demo.ipynb

Practical-RIFE/inference_img.py

Practical-RIFE/inference_img_SR.py

Practical-RIFE/inference_video.py

Practical-RIFE/inference_video_enhance.py

Practical-RIFE/model/__pycache__/loss.cpython-310.pyc

Practical-RIFE/model/__pycache__/warplayer.cpython-310.pyc

Practical-RIFE/model/loss.py

Practical-RIFE/model/pytorch_msssim/__init__.py

Practical-RIFE/model/pytorch_msssim/__pycache__/__init__.cpython-310.pyc

Practical-RIFE/model/warplayer.py

Practical-RIFE/train_log/.DS_Store

Practical-RIFE/train_log/IFNet_HDv3.py

Practical-RIFE/train_log/RIFE_HDv3.py

Practical-RIFE/train_log/__pycache__/IFNet_HDv3.cpython-310.pyc

Practical-RIFE/train_log/__pycache__/RIFE_HDv3.cpython-310.pyc

Practical-RIFE/train_log/flownet.pkl

Practical-RIFE/train_log/refine.py

README.md

__pycache__/handler.cpython-310.pyc

__pycache__/settings.cpython-310.pyc

assets/poses/align/img_downloaded_image_video_downloaded_video.mp4

assets/poses/align/img_rithwik_video_pose-2.mp4

clip/__init__.py

clip/bpe_simple_vocab_16e6.txt.gz

clip/clip.py

clip/clipseg.py

clip/model.py

clip/simple_tokenizer.py

clip/vitseg.py

config_colab.yaml

configs/inference/inference_v1.yaml

configs/inference/inference_v2.yaml

configs/prompts/animation.yaml

download_weights.py

extract_dwpose_from_vid.py

facefusion/.editorconfig

facefusion/.flake8

facefusion/.github/FUNDING.yml

facefusion/.github/workflows/ci.yml

facefusion/.gitignore

facefusion/.install/LICENSE.md

facefusion/.install/facefusion.ico

facefusion/.install/facefusion.nsi

facefusion/LICENSE.md

facefusion/README.md

facefusion/core.py

facefusion/facefusion.ini

facefusion/facefusion/__init__.py

facefusion/facefusion/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/__pycache__/audio.cpython-310.pyc

facefusion/facefusion/__pycache__/choices.cpython-310.pyc

facefusion/facefusion/__pycache__/common_helper.cpython-310.pyc

facefusion/facefusion/__pycache__/config.cpython-310.pyc

facefusion/facefusion/__pycache__/content_analyser.cpython-310.pyc

facefusion/facefusion/__pycache__/core.cpython-310.pyc

facefusion/facefusion/__pycache__/download.cpython-310.pyc

facefusion/facefusion/__pycache__/execution.cpython-310.pyc

facefusion/facefusion/__pycache__/face_analyser.cpython-310.pyc

facefusion/facefusion/__pycache__/face_helper.cpython-310.pyc

facefusion/facefusion/__pycache__/face_masker.cpython-310.pyc

facefusion/facefusion/__pycache__/face_store.cpython-310.pyc

facefusion/facefusion/__pycache__/ffmpeg.cpython-310.pyc

facefusion/facefusion/__pycache__/filesystem.cpython-310.pyc

facefusion/facefusion/__pycache__/globals.cpython-310.pyc

facefusion/facefusion/__pycache__/logger.cpython-310.pyc

facefusion/facefusion/__pycache__/memory.cpython-310.pyc

facefusion/facefusion/__pycache__/metadata.cpython-310.pyc

facefusion/facefusion/__pycache__/my_typing.cpython-310.pyc

facefusion/facefusion/__pycache__/normalizer.cpython-310.pyc

facefusion/facefusion/__pycache__/process_manager.cpython-310.pyc

facefusion/facefusion/__pycache__/statistics.cpython-310.pyc

facefusion/facefusion/__pycache__/thread_helper.cpython-310.pyc

facefusion/facefusion/__pycache__/typing.cpython-310.pyc

facefusion/facefusion/__pycache__/vision.cpython-310.pyc

facefusion/facefusion/__pycache__/voice_extractor.cpython-310.pyc

facefusion/facefusion/__pycache__/wording.cpython-310.pyc

facefusion/facefusion/audio.py

facefusion/facefusion/choices.py

facefusion/facefusion/common_helper.py

facefusion/facefusion/config.py

facefusion/facefusion/content_analyser.py

facefusion/facefusion/download.py

facefusion/facefusion/execution.py

facefusion/facefusion/face_analyser.py

facefusion/facefusion/face_helper.py

facefusion/facefusion/face_masker.py

facefusion/facefusion/face_store.py

facefusion/facefusion/ffmpeg.py

facefusion/facefusion/filesystem.py

facefusion/facefusion/globals.py

facefusion/facefusion/installer.py

facefusion/facefusion/logger.py

facefusion/facefusion/memory.py

facefusion/facefusion/metadata.py

facefusion/facefusion/my_typing.py

facefusion/facefusion/normalizer.py

facefusion/facefusion/process_manager.py

facefusion/facefusion/processors/__init__.py

facefusion/facefusion/processors/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/processors/frame/__init__.py

facefusion/facefusion/processors/frame/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/processors/frame/__pycache__/choices.cpython-310.pyc

facefusion/facefusion/processors/frame/__pycache__/core.cpython-310.pyc

facefusion/facefusion/processors/frame/__pycache__/globals.cpython-310.pyc

facefusion/facefusion/processors/frame/__pycache__/typings.cpython-310.pyc

facefusion/facefusion/processors/frame/choices.py

facefusion/facefusion/processors/frame/core.py

facefusion/facefusion/processors/frame/globals.py

facefusion/facefusion/processors/frame/modules/__init__.py

facefusion/facefusion/processors/frame/modules/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/face_debugger.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/face_enhancer.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/face_swapper.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/frame_colorizer.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/frame_enhancer.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/__pycache__/lip_syncer.cpython-310.pyc

facefusion/facefusion/processors/frame/modules/face_debugger.py

facefusion/facefusion/processors/frame/modules/face_enhancer.py

facefusion/facefusion/processors/frame/modules/face_swapper.py

facefusion/facefusion/processors/frame/modules/frame_colorizer.py

facefusion/facefusion/processors/frame/modules/frame_enhancer.py

facefusion/facefusion/processors/frame/modules/lip_syncer.py

facefusion/facefusion/processors/frame/typings.py

facefusion/facefusion/statistics.py

facefusion/facefusion/thread_helper.py

facefusion/facefusion/uis/__init__.py

facefusion/facefusion/uis/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/uis/__pycache__/choices.cpython-310.pyc

facefusion/facefusion/uis/__pycache__/core.cpython-310.pyc

facefusion/facefusion/uis/__pycache__/overrides.cpython-310.pyc

facefusion/facefusion/uis/__pycache__/typing.cpython-310.pyc

facefusion/facefusion/uis/assets/fixes.css

facefusion/facefusion/uis/assets/overrides.css

facefusion/facefusion/uis/choices.py

facefusion/facefusion/uis/components/__init__.py

facefusion/facefusion/uis/components/__pycache__/__init__.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/about.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/common_options.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/execution.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/execution_queue_count.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/execution_thread_count.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/face_analyser.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/face_masker.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/face_selector.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/frame_processors.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/frame_processors_options.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/memory.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/output.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/output_options.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/preview.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/source.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/target.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/temp_frame.cpython-310.pyc

facefusion/facefusion/uis/components/__pycache__/trim_frame.cpython-310.pyc

facefusion/facefusion/uis/components/about.py

facefusion/facefusion/uis/components/benchmark.py

facefusion/facefusion/uis/components/benchmark_options.py

facefusion/facefusion/uis/components/common_options.py

facefusion/facefusion/uis/components/execution.py

facefusion/facefusion/uis/components/execution_queue_count.py

facefusion/facefusion/uis/components/execution_thread_count.py

facefusion/facefusion/uis/components/face_analyser.py

facefusion/facefusion/uis/components/face_masker.py

facefusion/facefusion/uis/components/face_selector.py

facefusion/facefusion/uis/components/frame_processors.py

facefusion/facefusion/uis/components/frame_processors_options.py

facefusion/facefusion/uis/components/memory.py

facefusion/facefusion/uis/components/output.py

facefusion/facefusion/uis/components/output_options.py

facefusion/facefusion/uis/components/preview.py

facefusion/facefusion/uis/components/source.py

facefusion/facefusion/uis/components/target.py

facefusion/facefusion/uis/components/temp_frame.py

facefusion/facefusion/uis/components/trim_frame.py

facefusion/facefusion/uis/components/webcam.py

facefusion/facefusion/uis/components/webcam_options.py

facefusion/facefusion/uis/core.py

facefusion/facefusion/uis/layouts/__pycache__/default.cpython-310.pyc

facefusion/facefusion/uis/layouts/benchmark.py

facefusion/facefusion/uis/layouts/default.py

facefusion/facefusion/uis/layouts/webcam.py

facefusion/facefusion/uis/overrides.py

facefusion/facefusion/uis/typing.py

facefusion/facefusion/vision.py

facefusion/facefusion/voice_extractor.py

facefusion/facefusion/wording.py

facefusion/install.py

facefusion/mypy.ini

facefusion/requirements.txt

facefusion/run.py

facefusion/tests/__init__.py

facefusion/tests/test_audio.py

facefusion/tests/test_cli_face_debugger.py

facefusion/tests/test_cli_face_enhancer.py

facefusion/tests/test_cli_face_swapper.py

facefusion/tests/test_cli_frame_colorizer.py

facefusion/tests/test_cli_frame_enhancer.py

facefusion/tests/test_cli_lip_syncer.py

facefusion/tests/test_common_helper.py

facefusion/tests/test_config.py

facefusion/tests/test_download.py

facefusion/tests/test_execution.py

facefusion/tests/test_face_analyser.py

facefusion/tests/test_ffmpeg.py

facefusion/tests/test_filesystem.py

facefusion/tests/test_memory.py

facefusion/tests/test_normalizer.py

facefusion/tests/test_process_manager.py

facefusion/tests/test_vision.py

facefusion/tests/test_wording.py

gfpgan/weights/detection_Resnet50_Final.pth

gfpgan/weights/parsing_parsenet.pth

good_face.jpeg

handler.py

inference_img.py

inference_img_SR.py

inference_video.py

inference_video_enhance.py

installer/installer.py

installer/windows_run.bat

memory_stats.log

model/__pycache__/loss.cpython-310.pyc

model/__pycache__/warplayer.cpython-310.pyc

model/loss.py

model/pytorch_msssim/__init__.py

model/pytorch_msssim/__pycache__/__init__.cpython-310.pyc

model/warplayer.py

models/CLIP/rd64-uni-refined.pth

models/CodeFormer/CodeFormerv0.1.onnx ONNX

models/DMDNet.pth

models/Frame/deoldify_artistic.onnx ONNX

models/Frame/deoldify_stable.onnx ONNX

models/Frame/isnet-general-use.onnx ONNX

models/Frame/lsdir_x4.onnx ONNX

models/Frame/real_esrgan_x2.onnx ONNX

models/Frame/real_esrgan_x4.onnx ONNX

models/GFPGANv1.4.onnx ONNX

models/GFPGANv1.4.pth

models/GPEN-BFR-512.onnx ONNX

models/buffalo_l.zip

models/buffalo_l/1k3d68.onnx ONNX

models/buffalo_l/2d106det.onnx ONNX

models/buffalo_l/det_10g.onnx ONNX

models/buffalo_l/genderage.onnx ONNX

models/buffalo_l/w600k_r50.onnx ONNX

models/inswapper_128.onnx ONNX

models/restoreformer_plus_plus.onnx ONNX

models/xseg.onnx ONNX

mypy.ini

post_install.sh

pretrained_weights/DWPose/dw-ll_ucoco_384.onnx ONNX

pretrained_weights/DWPose/yolox_l.onnx ONNX

pretrained_weights/denoising_unet.pth

pretrained_weights/image_encoder/config.json

pretrained_weights/image_encoder/pytorch_model.bin

pretrained_weights/motion_module.pth

pretrained_weights/pose_guider.pth

pretrained_weights/reference_unet.pth

pretrained_weights/sd-vae-ft-mse/config.json

pretrained_weights/sd-vae-ft-mse/diffusion_pytorch_model.bin

pretrained_weights/stable-diffusion-v1-5/unet/config.json

pretrained_weights/stable-diffusion-v1-5/unet/diffusion_pytorch_model.bin

rembg_video.py

requirements.txt

roop-unleashed.ipynb

run.py

sampler.py

settings.py

src/__init__.py

src/__pycache__/__init__.cpython-310.pyc

src/dataset/dance_image.py

src/dataset/dance_video.py

src/dwpose/__init__.py

src/dwpose/__pycache__/__init__.cpython-310.pyc

src/dwpose/__pycache__/onnxdet.cpython-310.pyc

src/dwpose/__pycache__/onnxpose.cpython-310.pyc

src/dwpose/__pycache__/util.cpython-310.pyc

src/dwpose/__pycache__/wholebody.cpython-310.pyc

src/dwpose/onnxdet.py

src/dwpose/onnxpose.py

src/dwpose/util.py

src/dwpose/wholebody.py

src/models/__pycache__/attention.cpython-310.pyc

src/models/__pycache__/motion_module.cpython-310.pyc

src/models/__pycache__/mutual_self_attention.cpython-310.pyc

src/models/__pycache__/pose_guider.cpython-310.pyc

src/models/__pycache__/resnet.cpython-310.pyc

src/models/__pycache__/src_models_pose_guider.cpython-310.pyc

src/models/__pycache__/transformer_2d.cpython-310.pyc

src/models/__pycache__/transformer_3d.cpython-310.pyc

src/models/__pycache__/unet_2d_blocks.cpython-310.pyc

src/models/__pycache__/unet_2d_condition.cpython-310.pyc

src/models/__pycache__/unet_3d.cpython-310.pyc

src/models/__pycache__/unet_3d_blocks.cpython-310.pyc

src/models/attention.py

src/models/motion_module.py

src/models/mutual_self_attention.py

src/models/pose_guider.py

src/models/resnet.py

src/models/transformer_2d.py

src/models/transformer_3d.py

src/models/unet_2d_blocks.py

src/models/unet_2d_condition.py

src/models/unet_3d.py

src/models/unet_3d_blocks.py

src/pipelines/__init__.py

src/pipelines/__pycache__/__init__.cpython-310.pyc

src/pipelines/__pycache__/context.cpython-310.pyc

src/pipelines/__pycache__/pipeline_pose2vid_long.cpython-310.pyc

src/pipelines/__pycache__/utils.cpython-310.pyc

src/pipelines/context.py

src/pipelines/pipeline_pose2vid.py

src/pipelines/pipeline_pose2vid_long.py

src/pipelines/utils.py

src/utils/__pycache__/util.cpython-310.pyc

src/utils/download_models.py

src/utils/util.py

tools/download_weights.py

tools/extract_meta_info.py

tools/facetracker_api.py

tools/vid2pose.py

train_log/.DS_Store

train_log/IFNet_HDv3.py

train_log/RIFE_HDv3.py

train_log/__pycache__/IFNet_HDv3.cpython-310.pyc

train_log/__pycache__/RIFE_HDv3.cpython-310.pyc

train_log/flownet.pkl

train_log/refine.py

ui/globals.py

ui/main.py

ui/tabs/extras_tab.py

ui/tabs/facemgr_tab.py

ui/tabs/faceswap_tab.py

ui/tabs/livecam_tab.py

ui/tabs/settings_tab.py