-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' of github.com:Winfredy/SadTalker
- Loading branch information
Showing
6 changed files
with
337 additions
and
133 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
|
|
||
|
|
||
|
|
||
| ### Windows Native | ||
|
|
||
| - Make sure you have `ffmpeg` in the `%PATH%` as suggested in [#54](https://github.com/Winfredy/SadTalker/issues/54), following [this](https://www.geeksforgeeks.org/how-to-install-ffmpeg-on-windows/) installation to install `ffmpeg`. | ||
|
|
||
|
|
||
| ### Windows WSL | ||
| - Make sure the environment: `export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH` | ||
|
|
||
|
|
||
| ### Docker installnation | ||
|
|
||
| A dockerfile are also provided by [@thegenerativegeneration](https://github.com/thegenerativegeneration) in [docker hub](https://hub.docker.com/repository/docker/wawa9000/sadtalker), which can be used directly as: | ||
|
|
||
| ```bash | ||
| docker run --gpus "all" --rm -v $(pwd):/host_dir wawa9000/sadtalker \ | ||
| --driven_audio /host_dir/deyu.wav \ | ||
| --source_image /host_dir/image.jpg \ | ||
| --expression_scale 1.0 \ | ||
| --still \ | ||
| --result_dir /host_dir | ||
| ``` | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,12 +1,13 @@ | ||
| mkdir ./checkpoints | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/auido2exp_00300-model.pth -O ./checkpoints/auido2exp_00300-model.pth | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/auido2pose_00140-model.pth -O ./checkpoints/auido2pose_00140-model.pth | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/epoch_20.pth -O ./checkpoints/epoch_20.pth | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/facevid2vid_00189-model.pth.tar -O ./checkpoints/facevid2vid_00189-model.pth.tar | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/shape_predictor_68_face_landmarks.dat -O ./checkpoints/shape_predictor_68_face_landmarks.dat | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/wav2lip.pth -O ./checkpoints/wav2lip.pth | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/mapping_00229-model.pth.tar -O ./checkpoints/mapping_00229-model.pth.tar | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/BFM_Fitting.zip -O ./checkpoints/BFM_Fitting.zip | ||
| wget https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/hub.zip -O ./checkpoints/hub.zip | ||
| unzip ./checkpoints/hub.zip -d ./checkpoints/ | ||
| unzip ./checkpoints/BFM_Fitting.zip -d ./checkpoints/ | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/auido2exp_00300-model.pth -O ./checkpoints/auido2exp_00300-model.pth | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/auido2pose_00140-model.pth -O ./checkpoints/auido2pose_00140-model.pth | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/epoch_20.pth -O ./checkpoints/epoch_20.pth | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/facevid2vid_00189-model.pth.tar -O ./checkpoints/facevid2vid_00189-model.pth.tar | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/shape_predictor_68_face_landmarks.dat -O ./checkpoints/shape_predictor_68_face_landmarks.dat | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/wav2lip.pth -O ./checkpoints/wav2lip.pth | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/mapping_00229-model.pth.tar -O ./checkpoints/mapping_00229-model.pth.tar | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/BFM_Fitting.zip -O ./checkpoints/BFM_Fitting.zip | ||
| wget -nc https://github.com/Winfredy/SadTalker/releases/download/v0.0.1/hub.zip -O ./checkpoints/hub.zip | ||
|
|
||
| unzip -n ./checkpoints/hub.zip -d ./checkpoints/ | ||
| unzip -n ./checkpoints/BFM_Fitting.zip -d ./checkpoints/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,133 @@ | ||
| import os, sys | ||
| from pathlib import Path | ||
| import tempfile | ||
| import gradio as gr | ||
| from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call | ||
| from modules.shared import opts, OptionInfo | ||
| from modules import shared, paths, script_callbacks | ||
| import launch | ||
| import glob | ||
|
|
||
| def get_source_image(image): | ||
| return image | ||
|
|
||
| def get_img_from_txt2img(x): | ||
| talker_path = Path(paths.script_path) / "outputs" | ||
| imgs_from_txt_dir = str(talker_path / "txt2img-images/") | ||
| imgs = glob.glob(imgs_from_txt_dir+'/*/*.png') | ||
| imgs.sort(key=lambda x:os.path.getmtime(os.path.join(imgs_from_txt_dir, x))) | ||
| img_from_txt_path = os.path.join(imgs_from_txt_dir, imgs[-1]) | ||
| return img_from_txt_path, img_from_txt_path | ||
|
|
||
| def get_img_from_img2img(x): | ||
| talker_path = Path(paths.script_path) / "outputs" | ||
| imgs_from_img_dir = str(talker_path / "img2img-images/") | ||
| imgs = glob.glob(imgs_from_img_dir+'/*/*.png') | ||
| imgs.sort(key=lambda x:os.path.getmtime(os.path.join(imgs_from_img_dir, x))) | ||
| img_from_img_path = os.path.join(imgs_from_img_dir, imgs[-1]) | ||
| return img_from_img_path, img_from_img_path | ||
|
|
||
| def install(): | ||
|
|
||
| kv = { | ||
| "face-alignment": "face-alignment==1.3.5", | ||
| "imageio": "imageio==2.19.3", | ||
| "imageio-ffmpeg": "imageio-ffmpeg==0.4.7", | ||
| "librosa":"librosa==0.8.0", | ||
| "pydub":"pydub==0.25.1", | ||
| "scipy":"scipy==1.8.1", | ||
| "tqdm": "tqdm", | ||
| "yacs":"yacs==0.1.8", | ||
| "pyyaml": "pyyaml", | ||
| "dlib": "dlib-bin", | ||
| "gfpgan": "gfpgan", | ||
| } | ||
|
|
||
| for k,v in kv.items(): | ||
| print(k, launch.is_installed(k)) | ||
| if not launch.is_installed(k): | ||
| launch.run_pip("install "+ v, "requirements for SadTalker") | ||
|
|
||
|
|
||
| if os.getenv('SADTALKER_CHECKPOINTS'): | ||
| print('load Sadtalker Checkpoints from '+ os.getenv('SADTALKER_CHECKPOINTS')) | ||
| else: | ||
| ### run the scripts to downlod models to correct localtion. | ||
| print('download models for SadTalker') | ||
| launch.run("cd " + paths.script_path+"/extensions/SadTalker && bash ./scripts/download_models.sh", live=True) | ||
| print('SadTalker is successfully installed!') | ||
|
|
||
|
|
||
| def on_ui_tabs(): | ||
| install() | ||
|
|
||
| sys.path.extend([paths.script_path+'/extensions/SadTalker']) | ||
|
|
||
| repo_dir = paths.script_path+'/extensions/SadTalker/' | ||
|
|
||
| result_dir = opts.sadtalker_result_dir | ||
| os.makedirs(result_dir, exist_ok=True) | ||
|
|
||
| from src.gradio_demo import SadTalker | ||
|
|
||
| if os.getenv('SADTALKER_CHECKPOINTS'): | ||
| checkpoint_path = os.getenv('SADTALKER_CHECKPOINTS') | ||
| else: | ||
| checkpoint_path = repo_dir+'checkpoints/' | ||
|
|
||
| sad_talker = SadTalker(checkpoint_path=checkpoint_path, config_path=repo_dir+'src/config', lazy_load=True) | ||
|
|
||
| with gr.Blocks(analytics_enabled=False) as audio_to_video: | ||
| with gr.Row().style(equal_height=False): | ||
| with gr.Column(variant='panel'): | ||
| with gr.Tabs(elem_id="sadtalker_source_image"): | ||
| with gr.TabItem('Upload image'): | ||
| with gr.Row(): | ||
| input_image = gr.Image(label="Source image", source="upload", type="filepath").style(height=512,width=512) | ||
|
|
||
| with gr.Row(): | ||
| submit_image2 = gr.Button('load From txt2img', variant='primary') | ||
| submit_image2.click(fn=get_img_from_txt2img, inputs=input_image, outputs=[input_image, input_image]) | ||
|
|
||
| submit_image3 = gr.Button('load from img2img', variant='primary') | ||
| submit_image3.click(fn=get_img_from_img2img, inputs=input_image, outputs=[input_image, input_image]) | ||
|
|
||
| with gr.Tabs(elem_id="sadtalker_driven_audio"): | ||
| with gr.TabItem('Upload'): | ||
| with gr.Column(variant='panel'): | ||
|
|
||
| with gr.Row(): | ||
| driven_audio = gr.Audio(label="Input audio", source="upload", type="filepath") | ||
|
|
||
|
|
||
| with gr.Column(variant='panel'): | ||
| with gr.Tabs(elem_id="sadtalker_checkbox"): | ||
| with gr.TabItem('Settings'): | ||
| with gr.Column(variant='panel'): | ||
| is_still_mode = gr.Checkbox(label="Still Mode (fewer head motion)").style(container=True) | ||
| is_enhance_mode = gr.Checkbox(label="Enhance Mode (better face quality )").style(container=True) | ||
| submit = gr.Button('Generate', elem_id="sadtalker_generate", variant='primary') | ||
|
|
||
| with gr.Tabs(elem_id="sadtalker_genearted"): | ||
| gen_video = gr.Video(label="Generated video", format="mp4").style(width=256) | ||
|
|
||
|
|
||
| ### gradio gpu call will always return the html, | ||
| submit.click( | ||
| fn=wrap_queued_call(sad_talker.test), | ||
| inputs=[input_image, | ||
| driven_audio, | ||
| is_still_mode, | ||
| is_enhance_mode], | ||
| outputs=[gen_video, ] | ||
| ) | ||
|
|
||
| return [(audio_to_video, "SadTalker", "extension")] | ||
|
|
||
| def on_ui_settings(): | ||
| talker_path = Path(paths.script_path) / "outputs" | ||
| section = ('extension', "SadTalker") | ||
| opts.add_option("sadtalker_result_dir", OptionInfo(str(talker_path / "SadTalker/"), "Path to save results of sadtalker", section=section)) | ||
|
|
||
| script_callbacks.on_ui_settings(on_ui_settings) | ||
| script_callbacks.on_ui_tabs(on_ui_tabs) |
Oops, something went wrong.