Spaces:
Runtime error
Runtime error
import gradio as gr | |
import os | |
import shutil | |
import yaml | |
import tempfile | |
import cv2 | |
import huggingface_hub | |
import subprocess | |
import threading | |
import torch | |
from subprocess import getoutput | |
is_shared_ui = False | |
# is_shared_ui = True if "fffiloni/MimicMotion" in os.environ['SPACE_ID'] else False | |
available_property = False if is_shared_ui else True | |
is_gpu_associated = torch.cuda.is_available() | |
gpu_info = getoutput('nvidia-smi') | |
def stream_output(pipe): | |
for line in iter(pipe.readline, ''): | |
print(line, end='') | |
pipe.close() | |
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' | |
) | |
huggingface_hub.hf_hub_download( | |
repo_id='yzd-v/DWPose', | |
filename='dw-ll_ucoco_384.onnx', | |
local_dir='./models/DWPose' | |
) | |
huggingface_hub.hf_hub_download( | |
repo_id='ixaac/MimicMotion', | |
filename='MimicMotion_1.pth', | |
local_dir='./models' | |
) | |
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}") | |
def check_outputs_folder(folder_path): | |
# Check if the folder exists | |
if os.path.exists(folder_path) and os.path.isdir(folder_path): | |
# Delete all contents inside the folder | |
for filename in os.listdir(folder_path): | |
file_path = os.path.join(folder_path, filename) | |
try: | |
if os.path.isfile(file_path) or os.path.islink(file_path): | |
os.unlink(file_path) # Remove file or link | |
elif os.path.isdir(file_path): | |
shutil.rmtree(file_path) # Remove directory | |
except Exception as e: | |
print(f'Failed to delete {file_path}. Reason: {e}') | |
else: | |
print(f'The folder {folder_path} does not exist.') | |
def check_for_mp4_in_outputs(): | |
# Define the path to the outputs folder | |
outputs_folder = './outputs' | |
# Check if the outputs folder exists | |
if not os.path.exists(outputs_folder): | |
return None | |
# Check if there is a .mp4 file in the outputs folder | |
mp4_files = [f for f in os.listdir(outputs_folder) if f.endswith('.mp4')] | |
# Return the path to the mp4 file if it exists | |
if mp4_files: | |
return os.path.join(outputs_folder, mp4_files[0]) | |
else: | |
return None | |
def get_video_fps(video_path): | |
# Open the video file | |
video_capture = cv2.VideoCapture(video_path) | |
if not video_capture.isOpened(): | |
raise ValueError("Error opening video file") | |
# Get the FPS value | |
fps = video_capture.get(cv2.CAP_PROP_FPS) | |
# Release the video capture object | |
video_capture.release() | |
return fps | |
def load_examples(ref_image_in, ref_video_in): | |
return "./examples/mimicmotion_result1_example.mp4" | |
def infer(ref_image_in, ref_video_in): | |
# check if 'outputs' dir exists and empty it if necessary | |
check_outputs_folder('./outputs') | |
# 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 = 16 | |
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, bufsize=1) | |
# Create threads to handle stdout and stderr | |
stdout_thread = threading.Thread(target=stream_output, args=(process.stdout,)) | |
stderr_thread = threading.Thread(target=stream_output, args=(process.stderr,)) | |
# Start the threads | |
stdout_thread.start() | |
stderr_thread.start() | |
# Wait for the process to complete and the threads to finish | |
process.wait() | |
stdout_thread.join() | |
stderr_thread.join() | |
print("Inference script finished with return code:", process.returncode) | |
# Print the outputs directory contents | |
print_directory_contents('./outputs') | |
# Call the function and print the result | |
mp4_file_path = check_for_mp4_in_outputs() | |
print(mp4_file_path) | |
return mp4_file_path | |
output_video = gr.Video(label="Output Video") | |
css = """ | |
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; | |
} | |
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; | |
} | |
""" | |
with gr.Blocks(css=css) as demo: | |
with gr.Column(): | |
gr.Markdown("# MimicMotion") | |
with gr.Row(): | |
with gr.Column(): | |
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 (A10G-large recommended).<br /> | |
A A10G-large costs <strong>US$1.50/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 experimenting with this demo | |
</p> | |
</div> | |
''', elem_id="warning-duplicate") | |
else: | |
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> | |
You have successfully associated a {gpu_info} GPU to the MimicMotion Space 🎉</h2> | |
<p class="custom-color"> | |
You will be billed by the minute from when you activated the GPU until when it is turned off. | |
</p> | |
</div> | |
''', elem_id="warning-ready") | |
with gr.Row(): | |
ref_image_in = gr.Image(label="Person Image Reference", type="filepath") | |
ref_video_in = gr.Video(label="Person Video Reference") | |
with gr.Accordion("Advanced Settings", open=False): | |
num_inference_steps = gr.Slider(label="num inference steps", minimum=12, maximum=50, value=25, step=1, interactive=available_property) | |
guidance_scale = gr.Slider(label="guidance scale", minimum=0.1, maximum=10, value=2, step=0.1, interactive=available_property) | |
output_frames_per_second = gr.Slider(label="fps", minimum=1, maximum=60, value=16, step=1, interactive=available_property) | |
seed = gr.Number(label="Seed", value=42, interactive=available_property) | |
submit_btn = gr.Button("Submit", interactive=available_property) | |
gr.Examples( | |
examples = [ | |
["./examples/demo1.jpg", "./examples/preview_1.mp4"] | |
], | |
fn = load_examples, | |
inputs = [ref_image_in, ref_video_in], | |
outputs = [output_video], | |
run_on_click = True, | |
cache_examples = False | |
) | |
output_video.render() | |
submit_btn.click( | |
fn = infer, | |
inputs = [ref_image_in, ref_video_in], | |
outputs = [output_video] | |
) | |
demo.launch(show_api=False, show_error=False) |