app.py

import gradio as gr
import os 
import yaml
import tempfile
import huggingface_hub
import subprocess

HF_TKN = os.environ.get("GATED_HF_TOKEN")
huggingface_hub.login(token=HF_TKN)

huggingface_hub.hf_hub_download(
    repo_id='yzd-v/DWPose',
    filename='yolox_l.onnx',
    local_dir='./models/DWPose',
    local_dir_use_symlinks=False,
)

huggingface_hub.hf_hub_download(
    repo_id='yzd-v/DWPose',
    filename='dw-ll_ucoco_384.onnx',
    local_dir='./models/DWPose',
    local_dir_use_symlinks=False,
)

huggingface_hub.hf_hub_download(
    repo_id='ixaac/MimicMotion',
    filename='MimicMotion_1.pth',
    local_dir='./models',
    local_dir_use_symlinks=False,
)

def print_directory_contents(path):
    for root, dirs, files in os.walk(path):
        level = root.replace(path, '').count(os.sep)
        indent = ' ' * 4 * (level)
        print(f"{indent}{os.path.basename(root)}/")
        subindent = ' ' * 4 * (level + 1)
        for f in files:
            print(f"{subindent}{f}")

# Path to the directory you want to print
directory_path = './models'

# Print the directory contents
print_directory_contents(directory_path)

def infer(ref_video_in, ref_image_in):
    # Create a temporary directory
    with tempfile.TemporaryDirectory() as temp_dir:
        print("Temporary directory created:", temp_dir)
    
        # Define the values for the variables
        ref_video_path = ref_video_in
        ref_image_path = ref_image_in
        num_frames = 16
        resolution = 576
        frames_overlap = 6
        num_inference_steps = 25
        noise_aug_strength = 0
        guidance_scale = 2.0
        sample_stride = 2
        fps = 12
        seed = 42
    
        # Create the data structure
        data = {
            'base_model_path': 'stabilityai/stable-video-diffusion-img2vid-xt-1-1',
            'ckpt_path': 'models/MimicMotion_1.pth',
            'test_case': [
                {
                    'ref_video_path': ref_video_path,
                    'ref_image_path': ref_image_path,
                    'num_frames': num_frames,
                    'resolution': resolution,
                    'frames_overlap': frames_overlap,
                    'num_inference_steps': num_inference_steps,
                    'noise_aug_strength': noise_aug_strength,
                    'guidance_scale': guidance_scale,
                    'sample_stride': sample_stride,
                    'fps': fps,
                    'seed': seed
                }
            ]
        }
    
        # Define the file path
        file_path = os.path.join(temp_dir, 'config.yaml')
    
        # Write the data to a YAML file
        with open(file_path, 'w') as file:
            yaml.dump(data, file, default_flow_style=False)
    
        print("YAML file 'config.yaml' created successfully in", file_path)

        # Execute the inference command
        command = ['python', 'inference.py', '--inference_config', file_path]
        process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
        # Print logs in real-time
        while True:
            output = process.stdout.readline()
            if output == '' and process.poll() is not None:
                break
            if output:
                print(output.strip())
        
        # Print any remaining output
        for output in process.stdout:
            print(output.strip())
        for error in process.stderr:
            print(error.strip())
        
        # Wait for the process to complete and get the return code
        return_code = process.wait()
        print("Inference script finished with return code:", return_code)
    
    
    return "done"

demo = gr.Interface(
    fn = infer,
    inputs = [gr.Video(), gr.Image(type="filepath")],
    outputs = [gr.Textbox()]
)

demo.launch()