| import os |
| import shutil |
| from huggingface_hub import snapshot_download |
| import gradio as gr |
| os.chdir(os.path.dirname(os.path.abspath(__file__))) |
| from scripts.inference import inference_process |
| import argparse |
| import uuid |
|
|
| is_shared_ui = True if "fudan-generative-ai/hallo" in os.environ['SPACE_ID'] else False |
|
|
| if(not is_shared_ui): |
| hallo_dir = snapshot_download(repo_id="fudan-generative-ai/hallo", local_dir="pretrained_models") |
|
|
| def run_inference(source_image, driving_audio, progress=gr.Progress(track_tqdm=True)): |
| if is_shared_ui: |
| raise gr.Error("This Space only works in duplicated instances") |
| |
| unique_id = uuid.uuid4() |
| |
| args = argparse.Namespace( |
| config='configs/inference/default.yaml', |
| source_image=source_image, |
| driving_audio=driving_audio, |
| output=f'output-{unique_id}.mp4', |
| pose_weight=1.0, |
| face_weight=1.0, |
| lip_weight=1.0, |
| face_expand_ratio=1.2, |
| checkpoint=None |
| ) |
| |
| inference_process(args) |
| return f'output-{unique_id}.mp4' |
|
|
|
|
| css = ''' |
| div#warning-ready { |
| background-color: #ecfdf5; |
| padding: 0 16px 16px; |
| margin: 20px 0; |
| color: #030303!important; |
| } |
| div#warning-ready > .gr-prose > h2, div#warning-ready > .gr-prose > p { |
| color: #057857!important; |
| } |
| div#warning-duplicate { |
| background-color: #ebf5ff; |
| padding: 0 16px 16px; |
| margin: 20px 0; |
| color: #030303!important; |
| } |
| div#warning-duplicate > .gr-prose > h2, div#warning-duplicate > .gr-prose > p { |
| color: #0f4592!important; |
| } |
| div#warning-duplicate strong { |
| color: #0f4592; |
| } |
| p.actions { |
| display: flex; |
| align-items: center; |
| margin: 20px 0; |
| } |
| div#warning-duplicate .actions a { |
| display: inline-block; |
| margin-right: 10px; |
| } |
| .dark #warning-duplicate { |
| background-color: #0c0c0c !important; |
| border: 1px solid white !important; |
| } |
| ''' |
|
|
| with gr.Blocks(css=css) as demo: |
| if is_shared_ui: |
| top_description = gr.HTML(f''' |
| <div class="gr-prose"> |
| <h2 class="custom-color"><svg xmlns="http://www.w3.org/2000/svg" width="18px" height="18px" style="margin-right: 0px;display: inline-block;"fill="none"><path fill="#fff" d="M7 13.2a6.3 6.3 0 0 0 4.4-10.7A6.3 6.3 0 0 0 .6 6.9 6.3 6.3 0 0 0 7 13.2Z"/><path fill="#fff" fill-rule="evenodd" d="M7 0a6.9 6.9 0 0 1 4.8 11.8A6.9 6.9 0 0 1 0 7 6.9 6.9 0 0 1 7 0Zm0 0v.7V0ZM0 7h.6H0Zm7 6.8v-.6.6ZM13.7 7h-.6.6ZM9.1 1.7c-.7-.3-1.4-.4-2.2-.4a5.6 5.6 0 0 0-4 1.6 5.6 5.6 0 0 0-1.6 4 5.6 5.6 0 0 0 1.6 4 5.6 5.6 0 0 0 4 1.7 5.6 5.6 0 0 0 4-1.7 5.6 5.6 0 0 0 1.7-4 5.6 5.6 0 0 0-1.7-4c-.5-.5-1.1-.9-1.8-1.2Z" clip-rule="evenodd"/><path fill="#000" fill-rule="evenodd" d="M7 2.9a.8.8 0 1 1 0 1.5A.8.8 0 0 1 7 3ZM5.8 5.7c0-.4.3-.6.6-.6h.7c.3 0 .6.2.6.6v3.7h.5a.6.6 0 0 1 0 1.3H6a.6.6 0 0 1 0-1.3h.4v-3a.6.6 0 0 1-.6-.7Z" clip-rule="evenodd"/></svg> |
| Attention: this Space need to be duplicated to work</h2> |
| <p class="main-message custom-color"> |
| To make it work, <strong>duplicate the Space</strong> and run it on your own profile using a <strong>private</strong> GPU.<br /> |
| An L4 costs <strong>US$0.80/h</strong> |
| </p> |
| <p class="actions custom-color"> |
| <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}?duplicate=true"> |
| <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg-dark.svg" alt="Duplicate this Space" /> |
| </a> |
| to start generate your talking head |
| </p> |
| </div> |
| ''', elem_id="warning-duplicate") |
| gr.Markdown("# Demo for Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation") |
| gr.Markdown("Generate talking head avatars driven from audio. **5 seconds of audio takes >10 minutes to generate on an L4** - duplicate the space for private use or try for free on Google Colab") |
| gr.Markdown(""" |
| Hallo has a few simple requirements for input data: |
| |
| For the source image: |
| |
| 1. It should be cropped into squares. |
| 2. The face should be the main focus, making up 50%-70% of the image. |
| 3. The face should be facing forward, with a rotation angle of less than 30° (no side profiles). |
| |
| For the driving audio: |
| |
| 1. It must be in WAV format. |
| 2. It must be in English since our training datasets are only in this language. |
| 3. Ensure the vocals are clear; background music is acceptable. |
| |
| We have provided some [samples](https://huggingface.co/datasets/fudan-generative-ai/hallo_inference_samples) for your reference. |
| """) |
| with gr.Row(): |
| with gr.Column(): |
| avatar_face = gr.Image(type="filepath", label="Face") |
| driving_audio = gr.Audio(type="filepath", label="Driving audio") |
| generate = gr.Button("Generate") |
| with gr.Column(): |
| output_video = gr.Video(label="Your talking head") |
|
|
| generate.click( |
| fn=run_inference, |
| inputs=[avatar_face, driving_audio], |
| outputs=output_video |
| ) |
| |
| demo.launch() |
