newfile

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +32,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoints/BFM_Fitting/01_MorphableModel.mat filter=lfs diff=lfs merge=lfs -text
+checkpoints/BFM_Fitting/BFM09_model_info.mat filter=lfs diff=lfs merge=lfs -text
+checkpoints/facevid2vid_00189-model.pth.tar filter=lfs diff=lfs merge=lfs -text
+checkpoints/mapping_00229-model.pth.tar filter=lfs diff=lfs merge=lfs -text
+checkpoints/shape_predictor_68_face_landmarks.dat filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/chinese_news.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/deyu.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/eluosi.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/fayu.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/imagine.wav filter=lfs diff=lfs merge=lfs -text
+examples/driven_audio/japanese.wav filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_16.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_17.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_3.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_4.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_5.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_8.png filter=lfs diff=lfs merge=lfs -text
+examples/source_image/art_9.png filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,159 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+results/
+checkpoints/
+gradio_cached_examples/
+gfpgan/
+start.sh

Dockerfile

@@ -0,0 +1,59 @@
+FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+    git \
+    zip \
+    unzip \
+    git-lfs \
+    wget \
+    curl \
+    # ffmpeg \
+    ffmpeg \
+    x264 \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ENV PYTHON_VERSION=3.10.9
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel
+
+RUN pip install --no-cache-dir -U torch==1.12.1 torchvision==0.13.1
+COPY --chown=1000 requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir -U -r /tmp/requirements.txt
+
+COPY --chown=1000 . ${HOME}/app
+RUN ls -a
+ENV PYTHONPATH=${HOME}/app \
+    PYTHONUNBUFFERED=1 \
+    GRADIO_ALLOW_FLAGGING=never \
+    GRADIO_NUM_PORTS=1 \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_THEME=huggingface \
+    SYSTEM=spaces
+CMD ["python", "app.py"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Tencent AI Lab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,13 +1,14 @@
 ---
-title: Ninehertz Ai Head
-emoji: 🐢
-colorFrom: blue
-colorTo: pink
+title: ninehertzaihead
+emoji: 😎
+colorFrom: purple
+colorTo: green
 sdk: gradio
-sdk_version: 5.29.1
+sdk_version: 3.50.2
 app_file: app.py
 pinned: false
-license: unknown
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,341 @@
+import os, sys
+import tempfile
+import gradio as gr
+from src.gradio_demo import SadTalker  
+from huggingface_hub import snapshot_download
+
+def get_source_image(image):   
+    return image
+
+try:
+    import webui
+    in_webui = True
+except:
+    in_webui = False
+
+def toggle_audio_file(choice):
+    if choice == False:
+        return gr.update(visible=True), gr.update(visible=False)
+    else:
+        return gr.update(visible=False), gr.update(visible=True)
+    
+def ref_video_fn(path_of_ref_video):
+    if path_of_ref_video is not None:
+        return gr.update(value=True)
+    else:
+        return gr.update(value=False)
+    
+def download_model():
+    REPO_ID = 'ashishninehertz/modelforfacetalk'
+    snapshot_download(repo_id=REPO_ID, local_dir='./checkpoints', local_dir_use_symlinks=True)
+
+def animatalk_demo():
+    download_model()
+    animatalker = SadTalker(lazy_load=True)
+
+    custom_theme = gr.themes.Default(
+        primary_hue="blue",
+        secondary_hue="teal",
+        neutral_hue="slate",
+        radius_size="md",
+        font=[gr.themes.GoogleFont("Poppins"), "ui-sans-serif", "system-ui", "sans-serif"],
+    ).set(
+        button_primary_background_fill="linear-gradient(90deg, #2563eb 0%, #7c3aed 100%)",
+        button_primary_background_fill_hover="linear-gradient(90deg, #1d4ed8 0%, #6d28d9 100%)",
+        button_primary_text_color="white",
+        button_primary_background_fill_dark="linear-gradient(90deg, #3b82f6 0%, #8b5cf6 100%)",
+    )
+
+    with gr.Blocks(theme=custom_theme, analytics_enabled=False) as animatalk_interface:
+        gr.HTML("""
+        <div style="text-align: center; margin-bottom: 20px;">
+            <h1 style="font-size: 2.5rem; margin-bottom: 10px; background: linear-gradient(90deg, #2563eb 0%, #7c3aed 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent; animation: fadeIn 2s;">
+                AnimaTalk: AI-Powered Talking Face Animation
+            </h1>
+            <p style="font-size: 1.1rem; color: #6b7280;">
+                Bring your images to life with realistic facials animations
+            </p>
+        </div>
+        <style>
+            @keyframes fadeIn {
+                from { opacity: 0; }
+                to { opacity: 1; }
+            }
+            .gradient-border {
+                border: 3px solid;
+                border-image: linear-gradient(90deg, #2563eb 0%, #7c3aed 100%) 1;
+                animation: borderPulse 4s infinite;
+            }
+            @keyframes borderPulse {
+                0% { border-image: linear-gradient(90deg, #2563eb 0%, #7c3aed 100%) 1; }
+                50% { border-image: linear-gradient(90deg, #7c3aed 0%, #2563eb 100%) 1; }
+                100% { border-image: linear-gradient(90deg, #2563eb 0%, #7c3aed 100%) 1; }
+            }
+        </style>
+        """)
+        
+        with gr.Row():
+            with gr.Column(variant='panel', min_width=500):
+                with gr.Tabs():
+                    with gr.TabItem('Source Image', id="source_image"):
+                        source_image = gr.Image(
+                            label="Upload your image",
+                            source="upload",
+                            type="filepath",
+                            elem_id="source_img",
+                            interactive=True
+                        )
+                
+                with gr.Tabs():
+                    # with gr.TabItem('Animation Settings', id="driven_audio"):
+                    #     gr.Markdown("""
+                    #     <div style="background: #f8fafc; padding: 15px; border-radius: 8px; margin-bottom: 15px;">
+                    #         <b>Animation Options:</b><br>
+                    #         1. Audio only<br>
+                    #         2. Audio + Reference Video<br>
+                    #         3. Idle animation only<br>
+                    #         4. Reference video only
+                    #     </div>
+                    #     """)
+                        
+                        with gr.Row():
+                            driven_audio = gr.Audio(
+                                label="Upload audio file",
+                                source="upload",
+                                type="filepath",
+                                max_length=180,
+                                visible=True
+                            )
+                            driven_audio_no = gr.Audio(
+                                label="No audio needed for idle mode",
+                                source="upload",
+                                type="filepath",
+                                visible=False
+                            )
+                            
+                            with gr.Column():
+                                use_idle_mode = gr.Checkbox(
+                                    label="Enable Idle Animation",
+                                    info="Generate animation without audio"
+                                )
+                                length_of_audio = gr.Number(
+                                    value=5,
+                                    label="Video length (seconds)",
+                                    precision=0
+                                )
+                                use_idle_mode.change(
+                                    toggle_audio_file,
+                                    inputs=use_idle_mode,
+                                    outputs=[driven_audio, driven_audio_no]
+                                )
+
+                        with gr.Row():
+                            ref_video = gr.Video(
+                                label="Reference Video (optional)",
+                                source="upload",
+                                type="filepath",
+                                interactive=True
+                            )
+                            
+                            with gr.Column():
+                                use_ref_video = gr.Checkbox(
+                                    label="Use Reference Video",
+                                    value=False
+                                )
+                                ref_info = gr.Radio(
+                                    ['pose', 'blink', 'pose+blink', 'all'],
+                                    value='pose',
+                                    label='Reference Style',
+                                    info="Select which aspects to copy from reference"
+                                )
+                                ref_video.change(
+                                    ref_video_fn,
+                                    inputs=ref_video,
+                                    outputs=[use_ref_video]
+                                )
+
+            with gr.Column(variant='panel'):
+                with gr.Tabs():
+                    with gr.TabItem('Generation Settings'):
+                        with gr.Column(variant='panel'):
+                            with gr.Row():
+                                pose_style = gr.Slider(
+                                    minimum=0,
+                                    maximum=45,
+                                    step=1,
+                                    label="Pose Style Intensity",
+                                    value=0
+                                )
+                                exp_weight = gr.Slider(
+                                    minimum=0,
+                                    maximum=3,
+                                    step=0.1,
+                                    label="Expression Strength",
+                                    value=1
+                                )
+                                blink_every = gr.Checkbox(
+                                    label="Enable Eye Blinking",
+                                    value=True
+                                )
+
+                            with gr.Row():
+                                size_of_image = gr.Radio(
+                                    [256, 512],
+                                    value=256,
+                                    label='Face Resolution',
+                                    info="Higher resolution needs more processing power"
+                                )
+                                preprocess_type = gr.Radio(
+                                    ['crop', 'resize', 'full', 'extcrop', 'extfull'],
+                                    value='crop',
+                                    label='Image Processing',
+                                    info="How to handle the input image"
+                                )
+                            
+                            with gr.Row():
+                                is_still_mode = gr.Checkbox(
+                                    label="Still Mode",
+                                    info="Reduces head movement for more stable results"
+                                )
+                                facerender = gr.Radio(
+                                    ['facevid2vid', 'pirender'],
+                                    value='facevid2vid',
+                                    label='Rendering Engine'
+                                )
+                                
+                            with gr.Row():
+                                batch_size = gr.Slider(
+                                    label="Generation Batch Size",
+                                    step=1,
+                                    maximum=10,
+                                    value=1,
+                                    info="Higher values process more at once"
+                                )
+                                enhancer = gr.Checkbox(
+                                    label="Enable Face Enhancer",
+                                    info="Improves face quality with GFPGAN"
+                                )
+                            
+                            submit = gr.Button(
+                                'Generate Animation',
+                                variant='primary',
+                                elem_classes="gradient-border"
+                            )
+                
+                with gr.Tabs():
+                    gen_video = gr.Video(
+                        label="Generated Animation",
+                        format="mp4",
+                        autoplay=True,
+                        elem_id="output_video"
+                    )
+
+        submit.click(
+            fn=animatalker.test,
+            inputs=[
+                source_image,
+                driven_audio,
+                preprocess_type,
+                is_still_mode,
+                enhancer,
+                batch_size,
+                size_of_image,
+                pose_style,
+                facerender,
+                exp_weight,
+                use_ref_video,
+                ref_video,
+                ref_info,
+                use_idle_mode,
+                length_of_audio,
+                blink_every
+            ],
+            outputs=[gen_video],
+        )
+
+        # with gr.Row():
+        #     examples = [
+        #         [
+        #             'examples/source_image/full_body_1.png',
+        #             'examples/driven_audio/bus_chinese.wav',
+        #             'crop',
+        #             True,
+        #             False
+        #         ],
+        #         [
+        #             'examples/source_image/full_body_2.png',
+        #             'examples/driven_audio/japanese.wav',
+        #             'crop',
+        #             False,
+        #             False
+        #         ],
+        #         [
+        #             'examples/source_image/full3.png',
+        #             'examples/driven_audio/deyu.wav',
+        #             'crop',
+        #             False,
+        #             True
+        #         ],
+        #         [
+        #             'examples/source_image/full4.jpeg',
+        #             'examples/driven_audio/eluosi.wav',
+        #             'full',
+        #             False,
+        #             True
+        #         ],
+        #         [
+        #             'examples/source_image/full4.jpeg',
+        #             'examples/driven_audio/imagine.wav',
+        #             'full',
+        #             True,
+        #             True
+        #         ],
+        #         [
+        #             'examples/source_image/full_body_1.png',
+        #             'examples/driven_audio/bus_chinese.wav',
+        #             'full',
+        #             True,
+        #             False
+        #         ],
+        #         [
+        #             'examples/source_image/art_13.png',
+        #             'examples/driven_audio/fayu.wav',
+        #             'resize',
+        #             True,
+        #             False
+        #         ],
+        #         [
+        #             'examples/source_image/art_5.png',
+        #             'examples/driven_audio/chinese_news.wav',
+        #             'resize',
+        #             False,
+        #             False
+        #         ],
+        #         [
+        #             'examples/source_image/art_5.png',
+        #             'examples/driven_audio/RD_Radio31_000.wav',
+        #             'resize',
+        #             True,
+        #             True
+        #         ],
+        #     ]
+        #     gr.Examples(
+        #         examples=examples,
+        #         inputs=[
+        #             source_image,
+        #             driven_audio,
+        #             preprocess_type,
+        #             is_still_mode,
+        #             enhancer
+        #         ],
+        #         outputs=[gen_video],
+        #         fn=animatalker.test,
+        #         cache_examples=os.getenv('SYSTEM') == 'spaces'
+        #     )
+
+    return animatalk_interface
+
+if __name__ == "__main__":
+    demo = animatalk_demo()
+    demo.queue(max_size=10, api_open=True)
+    demo.launch(debug=True)

examples/driven_audio/RD_Radio31_000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c9ccb3fd22f5bea782a2cd8ac6b60c4e8eb68b18a2eeeaa843b2bfb3c3dfbd
+size 512044

examples/driven_audio/RD_Radio34_002.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a0bfd5715cfde2a8e2effe3c776dbcb8e3a22aa872b5b682f00dc38780a631
+size 512044

examples/driven_audio/RD_Radio36_000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ab7eb00789418f29c25ae8abd00cf9c99f809a707311a6624d102b569cc13f
+size 512044

examples/driven_audio/RD_Radio40_000.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7469ca98f84a258decc5e4bc680f388f92d82a7da373c115ec3f452ca54c44e0
+size 512044

examples/driven_audio/bus_chinese.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6766dd6d56c019e2c30119b5a5a54b272adee22c5dddd163477065ea848a296b
+size 652276

examples/driven_audio/chinese_news.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0f4d313a1ca671bc4831d60bcf0c12225efbffe6c0e93e54fbfe9bcd4021cb
+size 1536078

examples/driven_audio/chinese_poem1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5488160b96cea9463582d86ec0b7a04fd83083f8448a8a9e5383dcdfb7578e
+size 262734

examples/driven_audio/chinese_poem2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eddce7d3a0679d81d370ff3cfb7de9929f47fa92a1eec1cb9af6a030c353c29
+size 460878

examples/driven_audio/deyu.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1839c57770a2ab0b593ce814344bfd4d750da02acc9be9e8cf5b9113a0f88a
+size 2694784

examples/driven_audio/eluosi.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a3593815dc7b68c256672baa61934c9479efa770af2065fb0886f02713606e
+size 1786672

examples/driven_audio/fayu.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ebd13626ae4171030b4ea05cceef06078483c352e4b68d469fc2a52bfffceb
+size 1940428

examples/driven_audio/imagine.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db410217e074d91ae6011e1c5dc0b94f02d05d381c50af8e54253eeacad17d2
+size 1618510

examples/driven_audio/itosinger1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ef5f7b4f01a68ca147e9f86f15a6e0414dd0044ba70d9a77268acae463adb8
+size 500012

examples/driven_audio/japanese.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db5426d0b158799e2be4f609b11f75bfbd4affffe18e9a1c8e6f241fcdedcfc
+size 2622712