Migrated from GitHub

.gitattributes

@@ -33,3 +33,41 @@ 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
+EMTD_dataset/ref_imgs_by_FLUX/man/0017.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0025.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0055.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0056.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0101.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0170.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0177.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0181.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0211.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0415.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/man/0424.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0010.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0035.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0057.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0101.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0163.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0175.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0201.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0247.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0253.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0284.png filter=lfs diff=lfs merge=lfs -text
+EMTD_dataset/ref_imgs_by_FLUX/woman/0287.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/audio/chinese/echomimicv2_woman.wav filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0014.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0035.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0047.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0057.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0066.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0082.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0140.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0163.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0175.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0213.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0216.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0222.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0247.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0303.png filter=lfs diff=lfs merge=lfs -text
+assets/halfbody_demo/refimag/natural_bk_openhand/0315.png filter=lfs diff=lfs merge=lfs -text

EMTD_dataset/download.py

@@ -0,0 +1,40 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+
+import os
+'''
+pip install youtube-dl==2020.12.12
+'''
+import subprocess
+import pandas as pd
+
+def download_youtube_video(video_url, output_path):
+    """
+    :param video_url: youtube video url
+    :param output_dir: file path to save
+    """
+    # video_url, output_path = info
+    try:
+        if not os.path.exists(os.path.dirname(output_path)):
+            os.makedirs(os.path.dirname(output_path), exist_ok=True)
+        # download command
+        command = ['yt-dlp', '-f', 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]', '--merge-output-format',
+               'mp4', '--output', output_path , video_url]
+        # subprocess.run
+        result = subprocess.run(command, capture_output=True, text=True, encoding='utf-8')
+
+        if result.returncode == 0:
+            print('Download {:s} successfully!'.format(video_url))
+        else:
+            print("Fail to download {:s}, error info:\n{:s}".format(video_url, result.stderr))
+    except Exception as e:
+        print(f"error: {e}")
+
+if __name__ == '__main__':
+    df = pd.read_csv("./echomimicv2_benchmark_url+start_timecode+end_timecode.txt")
+    save_dir = "ori_video_dir"
+    urls = list(set(df['URL']))
+    video_output_paths = [os.path.join(save_dir, url.split('v=')[1]+".mp4") for url in urls]
+
+    for video_url, output_path in zip(urls, video_output_paths):
+        download_youtube_video(video_url, output_path)

EMTD_dataset/echomimicv2_benchmark_url+start_timecode+end_timecode.txt

@@ -0,0 +1,111 @@
+URL,Start Timecode,End Timecode
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:00:54.596,00:01:01.561
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:02:04.207,00:02:11.006
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:03:06.103,00:03:13.819
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:03:51.231,00:03:56.445
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:05:39.047,00:05:43.677
+https://www.youtube.com/watch?v=NBMTc71yrpk,00:07:14.851,00:07:22.734
+https://www.youtube.com/watch?v=j4QlG5jKpio,00:02:31.777,00:02:41.328
+https://www.youtube.com/watch?v=j4QlG5jKpio,00:04:10.750,00:04:31.146
+https://www.youtube.com/watch?v=j4QlG5jKpio,00:06:25.135,00:06:38.231
+https://www.youtube.com/watch?v=j4QlG5jKpio,00:08:32.554,00:08:39.144
+https://www.youtube.com/watch?v=uEOK3fk45Rg,00:02:28.750,00:02:45.625
+https://www.youtube.com/watch?v=uEOK3fk45Rg,00:05:36.167,00:05:51.167
+https://www.youtube.com/watch?v=uEOK3fk45Rg,00:07:46.833,00:08:00.625
+https://www.youtube.com/watch?v=uEOK3fk45Rg,00:09:51.708,00:10:00.250
+https://www.youtube.com/watch?v=p8ReF00JP5w,00:02:10.417,00:02:18.583
+https://www.youtube.com/watch?v=p8ReF00JP5w,00:05:09.583,00:05:19.708
+https://www.youtube.com/watch?v=eIRtcspIH4U,00:04:43.950,00:05:59.025
+https://www.youtube.com/watch?v=eIRtcspIH4U,00:07:35.664,00:08:19.916
+https://www.youtube.com/watch?v=eIRtcspIH4U,00:10:17.867,00:10:32.924
+https://www.youtube.com/watch?app=desktop&v=R7jm0-R9N_o,00:02:39.493,00:02:55.609
+https://www.youtube.com/watch?app=desktop&v=R7jm0-R9N_o,00:04:15.088,00:04:41.114
+https://www.youtube.com/watch?app=desktop&v=R7jm0-R9N_o,00:06:08.635,00:06:42.035
+https://www.youtube.com/watch?app=desktop&v=R7jm0-R9N_o,00:08:08.288,00:08:19.532
+https://www.youtube.com/watch?app=desktop&v=R7jm0-R9N_o,00:09:52.659,00:10:10.009
+https://www.youtube.com/watch?app=desktop&v=whZmwSUMSVY,00:02:03.832,00:02:17.471
+https://www.youtube.com/watch?app=desktop&v=whZmwSUMSVY,00:05:18.610,00:05:29.496
+https://www.youtube.com/watch?app=desktop&v=whZmwSUMSVY,00:08:14.577,00:08:50.155
+https://www.youtube.com/watch?app=desktop&v=8cF442d-EdQ,00:06:30.720,00:07:25.360
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:00:38.360,00:00:42.880
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:01:21.320,00:01:35.840
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:01:56.920,00:02:00.760
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:04:38.160,00:04:44.440
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:05:12.520,00:05:16.880
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:05:45.680,00:05:51.480
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:06:12.640,00:06:18.880
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:07:00.640,00:07:08.200
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:09:23.480,00:09:27.680
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:09:50.640,00:09:53.920
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:10:17.560,00:10:22.360
+https://www.youtube.com/watch?v=U-BHz_UIOfs,00:10:49.880,00:10:58.000
+https://www.youtube.com/watch?v=FpiWSFcL3-c,00:07:14.100,00:07:18.938
+https://www.youtube.com/watch?v=FpiWSFcL3-c&t=355s,00:05:17.317,00:05:19.528
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:00:02.336,00:00:05.255
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:00:38.288,00:00:43.293
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:00:58.725,00:01:01.728
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:01:28.964,00:01:35.220
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:01:50.027,00:02:01.079
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:03:05.852,00:03:16.488
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:03:52.482,00:04:00.615
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:05:08.642,00:05:12.270
+https://www.youtube.com/watch?v=4SCrXqbhmCY,00:05:32.624,00:05:35.627
+https://www.youtube.com/watch?v=4c_xYLwOx-g,00:03:17.739,00:03:22.953
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:01:17.867,00:01:28.533
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:02:55.500,00:03:00.600
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:04:05.767,00:04:15.333
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:05:04.900,00:05:09.933
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:05:47.833,00:05:53.967
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:07:04.933,00:07:11.900
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:08:53.767,00:09:16.367
+https://www.youtube.com/watch?v=rVNb53lkBuc,00:11:40.333,00:11:45.500
+https://www.youtube.com/watch?v=PZr142ka96k,00:00:58.141,00:01:00.477
+https://www.youtube.com/watch?v=PZr142ka96k,00:03:11.358,00:03:17.030
+https://www.youtube.com/watch?v=6UiU99_tE7I,00:00:05.923,00:00:10.385
+https://www.youtube.com/watch?v=6UiU99_tE7I,00:00:48.215,00:00:51.343
+https://www.youtube.com/watch?v=6UiU99_tE7I,00:02:36.531,00:02:40.077
+https://www.youtube.com/watch?v=6UiU99_tE7I,00:04:08.498,00:04:17.299
+https://www.youtube.com/watch?v=MByKyFt7hZI,00:00:11.637,00:00:16.350
+https://www.youtube.com/watch?v=MByKyFt7hZI,00:02:46.958,00:03:02.432
+https://www.youtube.com/watch?v=MByKyFt7hZI,00:03:54.568,00:03:58.488
+https://www.youtube.com/watch?v=VU44eEKtcmQ,00:00:34.117,00:00:39.957
+https://www.youtube.com/watch?v=VU44eEKtcmQ,00:01:50.819,00:01:56.616
+https://www.youtube.com/watch?v=VU44eEKtcmQ,00:03:14.694,00:03:18.990
+https://www.youtube.com/watch?v=Dvhu2OK7ffg,00:01:53.905,00:01:56.992
+https://www.youtube.com/watch?v=Dvhu2OK7ffg,00:04:51.333,00:04:58.381
+https://www.youtube.com/watch?v=s0H1jxF5TWQ,00:01:55.699,00:01:58.452
+https://www.youtube.com/watch?v=x672EKnKLtA,00:00:55.389,00:01:01.895
+https://www.youtube.com/watch?v=Z3HJCQJ2Lmo,00:01:36.240,00:01:39.520
+https://www.youtube.com/watch?v=40TumEHQk8A,00:01:43.020,00:01:46.690
+https://www.youtube.com/watch?v=rXxUCeRVma4,00:02:51.880,00:02:58.887
+https://www.youtube.com/watch?v=v6mknkg7MEc,00:03:26.080,00:03:36.000
+https://www.youtube.com/watch?v=v6mknkg7MEc,00:06:09.880,00:06:32.120
+https://www.youtube.com/watch?v=v6mknkg7MEc,00:09:30.960,00:09:40.240
+https://www.youtube.com/watch?v=ixBgCWLVvE8,00:02:38.300,00:03:05.133
+https://www.youtube.com/watch?v=ixBgCWLVvE8,00:04:37.033,00:04:43.833
+https://www.youtube.com/watch?v=TQ2f4sJVXAI,00:01:22.900,00:01:47.133
+https://www.youtube.com/watch?v=dZtnOnqcDN4,00:00:48.067,00:01:12.667
+https://www.youtube.com/watch?v=dZtnOnqcDN4,00:04:09.833,00:04:23.867
+https://www.youtube.com/watch?v=dZtnOnqcDN4,00:07:25.733,00:07:52.067
+https://www.youtube.com/watch?v=dZtnOnqcDN4,00:09:41.000,00:10:02.233
+https://www.youtube.com/watch?v=-Hmn5Gmn2dw,00:04:40.208,00:04:49.458
+https://www.youtube.com/watch?v=x1Efv_wF5LE,00:05:35.833,00:05:41.733
+https://www.youtube.com/watch?v=VHMYl70ibHQ,00:03:41.500,00:04:15.833
+https://www.youtube.com/watch?v=fua_rUk0zk0,00:06:47.867,00:07:11.433
+https://www.youtube.com/watch?v=SfROjZlyg7o,00:03:26.400,00:03:38.960
+https://www.youtube.com/watch?v=SfROjZlyg7o,00:06:22.240,00:06:44.160
+https://www.youtube.com/watch?v=wBRqxBvBWQE,00:10:13.208,00:10:32.125
+https://www.youtube.com/watch?v=0BF2Np5J6jY,00:02:51.280,00:02:58.920
+https://www.youtube.com/watch?v=0BF2Np5J6jY,00:04:57.040,00:05:16.680
+https://www.youtube.com/watch?v=0BF2Np5J6jY,00:07:33.400,00:07:43.240
+https://www.youtube.com/watch?v=0BF2Np5J6jY,00:09:45.560,00:09:59.680
+https://www.youtube.com/watch?v=5FCPLlF6P4g,00:01:46.280,00:01:54.880
+https://www.youtube.com/watch?v=5FCPLlF6P4g,00:03:22.200,00:03:41.640
+https://www.youtube.com/watch?v=5FCPLlF6P4g,00:05:05.400,00:05:16.160
+https://www.youtube.com/watch?v=5FCPLlF6P4g,00:06:52.480,00:07:05.360
+https://www.youtube.com/watch?v=-BR9P4E7liU,00:01:52.320,00:02:03.360
+https://www.youtube.com/watch?v=-BR9P4E7liU,00:05:05.760,00:05:17.000
+https://www.youtube.com/watch?v=pxeJxyCiOJo,00:02:48.320,00:03:08.920
+https://www.youtube.com/watch?v=dKmHLAKQ5PI,00:05:55.337,00:06:01.998
+https://www.youtube.com/watch?app=desktop&v=lJUrQKY_A5g,00:04:36.208,00:04:50.958
+https://www.youtube.com/watch?app=desktop&v=lJUrQKY_A5g,00:08:21.583,00:08:43.042

EMTD_dataset/preprocess.py

@@ -0,0 +1,328 @@
+import sys
+
+from src.utils.img_utils import pil_to_cv2, cv2_to_pil, center_crop_cv2, pils_from_video, save_videos_from_pils, save_video_from_cv2_list
+from PIL import Image
+import cv2
+from IPython import embed
+import numpy as np
+import copy
+from src.utils.motion_utils import motion_sync
+import pathlib
+import torch
+import pickle
+from glob import glob
+import os
+from src.models.dwpose.dwpose_detector import dwpose_detector as dwprocessor
+from src.models.dwpose.util import draw_pose
+import decord
+from tqdm import tqdm
+from moviepy.editor import AudioFileClip, VideoFileClip
+from multiprocessing.pool import ThreadPool
+
+##################################
+base_dir = "root"
+tasks = ["emtd"]
+
+process_num = 800 #1266
+
+start = 0
+end = process_num + start
+#################################
+MAX_SIZE = 768
+
+
+def convert_fps(src_path, tgt_path, tgt_fps=24, tgt_sr=16000):
+    clip = VideoFileClip(src_path)
+    new_clip = clip.set_fps(tgt_fps)
+    if tgt_fps is not None:
+        audio = new_clip.audio
+        audio = audio.set_fps(tgt_sr)
+        new_clip = new_clip.set_audio(audio)
+    
+    new_clip.write_videofile(tgt_path, codec='libx264', audio_codec='aac')
+    
+def get_video_pose(
+        video_path: str, 
+        sample_stride: int=1,
+        max_frame=None):
+
+    # read input video
+    vr = decord.VideoReader(video_path, ctx=decord.cpu(0))
+    sample_stride *= max(1, int(vr.get_avg_fps() / 24))
+
+    frames = vr.get_batch(list(range(0, len(vr), sample_stride))).asnumpy()
+    if max_frame is not None:
+        frames = frames[0:max_frame,:,:]
+    height, width, _ = frames[0].shape
+    # detected_poses = [dwprocessor(frm) for frm in tqdm(frames, desc="DWPose")]
+    detected_poses = [dwprocessor(frm) for frm in frames]
+    dwprocessor.release_memory()
+
+    return detected_poses, height, width, frames
+    
+def resize_and_pad(img, max_size):
+    img_new = np.zeros((max_size, max_size, 3)).astype('uint8')
+    imh, imw = img.shape[0], img.shape[1]
+    half = max_size // 2
+    if imh > imw:
+        imh_new = max_size
+        imw_new = int(round(imw/imh * imh_new))
+        half_w = imw_new // 2
+        rb, re = 0, max_size
+        cb = half-half_w
+        ce = cb + imw_new
+    else:
+        imw_new = max_size
+        imh_new = int(round(imh/imw * imw_new))
+        half_h = imh_new // 2
+        cb, ce = 0, max_size
+        rb = half-half_h
+        re = rb + imh_new
+
+    img_resize = cv2.resize(img, (imw_new, imh_new))
+    img_new[rb:re,cb:ce,:] = img_resize
+    return img_new
+
+def resize_and_pad_param(imh, imw, max_size):
+    half = max_size // 2
+    if imh > imw:
+        imh_new = max_size
+        imw_new = int(round(imw/imh * imh_new))
+        half_w = imw_new // 2
+        rb, re = 0, max_size
+        cb = half-half_w
+        ce = cb + imw_new
+    else:
+        imw_new = max_size
+        imh_new = int(round(imh/imw * imw_new))
+        imh_new = max_size
+
+        half_h = imh_new // 2
+        cb, ce = 0, max_size
+        rb = half-half_h
+        re = rb + imh_new
+        
+    return imh_new, imw_new, rb, re, cb, ce
+
+def get_pose_params(detected_poses, max_size):
+    print('get_pose_params...')
+    # pose rescale 
+    w_min_all, w_max_all, h_min_all, h_max_all = [], [], [], []
+    mid_all = []
+    for num, detected_pose in enumerate(detected_poses):
+        detected_poses[num]['num'] = num
+        candidate_body = detected_pose['bodies']['candidate']
+        score_body = detected_pose['bodies']['score']
+        candidate_face = detected_pose['faces']
+        score_face = detected_pose['faces_score']
+        candidate_hand = detected_pose['hands']
+        score_hand = detected_pose['hands_score']
+
+        # 选取置信度最高的face
+        if candidate_face.shape[0] > 1:
+            index = 0
+            candidate_face = candidate_face[index]
+            score_face = score_face[index]
+            detected_poses[num]['faces'] = candidate_face.reshape(1, candidate_face.shape[0], candidate_face.shape[1])
+            detected_poses[num]['faces_score'] = score_face.reshape(1, score_face.shape[0])
+        else:
+            candidate_face = candidate_face[0]
+            score_face = score_face[0]
+
+        # 选取置信度最高的body
+        if score_body.shape[0] > 1:
+            tmp_score = []
+            for k in range(0, score_body.shape[0]):
+                tmp_score.append(score_body[k].mean())
+            index = np.argmax(tmp_score)
+            candidate_body = candidate_body[index*18:(index+1)*18,:]
+            score_body = score_body[index]
+            score_hand = score_hand[(index*2):(index*2+2),:]
+            candidate_hand = candidate_hand[(index*2):(index*2+2),:,:]
+        else:
+            score_body = score_body[0]
+        all_pose = np.concatenate((candidate_body, candidate_face))
+        all_score = np.concatenate((score_body, score_face))
+        all_pose = all_pose[all_score>0.8]
+
+
+        body_pose = np.concatenate((candidate_body,))
+        mid_ = body_pose[1, 0]
+
+
+        face_pose = candidate_face
+        hand_pose = candidate_hand
+
+
+        h_min, h_max = np.min(face_pose[:,1]), np.max(body_pose[:7,1])
+
+        h_ = h_max - h_min
+        
+        mid_w = mid_
+        w_min = mid_w - h_ // 2
+        w_max = mid_w + h_ // 2
+        
+        w_min_all.append(w_min)
+        w_max_all.append(w_max)
+        h_min_all.append(h_min)
+        h_max_all.append(h_max)
+        mid_all.append(mid_w)
+
+    w_min = np.min(w_min_all)
+    w_max = np.max(w_max_all)
+    h_min = np.min(h_min_all)
+    h_max = np.max(h_max_all)
+    mid = np.mean(mid_all)
+    print(mid)
+
+    margin_ratio = 0.25
+    h_margin = (h_max-h_min)*margin_ratio
+    
+    h_min = max(h_min-h_margin*0.65, 0)
+    h_max = min(h_max+h_margin*0.5, 1)
+
+    h_new = h_max - h_min
+    
+    h_min_real = int(h_min*height)
+    h_max_real = int(h_max*height)
+    mid_real = int(mid*width)
+    
+    
+    height_new = h_max_real-h_min_real+1
+    width_new = height_new
+    w_min_real = mid_real - height_new // 2
+
+    w_max_real = w_min_real + width_new
+    w_min = w_min_real / width
+    w_max = w_max_real / width
+
+    print(width_new, height_new)
+
+    imh_new, imw_new, rb, re, cb, ce = resize_and_pad_param(height_new, width_new, max_size)
+    res = {'draw_pose_params': [imh_new, imw_new, rb, re, cb, ce], 
+           'pose_params': [w_min, w_max, h_min, h_max],
+           'video_params': [h_min_real, h_max_real, w_min_real, w_max_real],
+           }
+    return res
+
+def save_pose_params_item(input_items):
+    detected_pose, pose_params, draw_pose_params, save_dir = input_items
+    w_min, w_max, h_min, h_max = pose_params
+    num = detected_pose['num']
+    candidate_body = detected_pose['bodies']['candidate']
+    candidate_face = detected_pose['faces'][0]
+    candidate_hand = detected_pose['hands']
+    candidate_body[:,0] = (candidate_body[:,0]-w_min)/(w_max-w_min)
+    candidate_body[:,1] = (candidate_body[:,1]-h_min)/(h_max-h_min)
+    candidate_face[:,0] = (candidate_face[:,0]-w_min)/(w_max-w_min)
+    candidate_face[:,1] = (candidate_face[:,1]-h_min)/(h_max-h_min)
+    candidate_hand[:,:,0] = (candidate_hand[:,:,0]-w_min)/(w_max-w_min)
+    candidate_hand[:,:,1] = (candidate_hand[:,:,1]-h_min)/(h_max-h_min)
+    detected_pose['bodies']['candidate'] = candidate_body
+    detected_pose['faces'] = candidate_face.reshape(1, candidate_face.shape[0], candidate_face.shape[1])
+    detected_pose['hands'] = candidate_hand
+    detected_pose['draw_pose_params'] = draw_pose_params
+    np.save(save_dir+'/'+str(num)+'.npy', detected_pose)
+
+def save_pose_params(detected_poses, pose_params, draw_pose_params, ori_video_path):
+    save_dir = ori_video_path.replace('original_videos', 'image_audio_features/pose/')
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+
+    input_list = []
+    for i, detected_pose in enumerate(detected_poses):
+        input_list.append([detected_pose, pose_params, draw_pose_params, save_dir])
+
+    pool = ThreadPool(8)
+    pool.map(save_pose_params_item, input_list)
+    pool.close()
+    pool.join()
+       
+def save_processed_video(ori_frames, video_params, ori_video_path, max_size):
+    save_path = ori_video_path.replace('original_videos', 'processed/video/')
+    save_dir = os.path.dirname(save_path)
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+    h_min_real, h_max_real, w_min_real, w_max_real = video_params
+    video_frame_crop = []
+    for img in ori_frames:
+        img = img[h_min_real:h_max_real,w_min_real:w_max_real,:]
+        img = resize_and_pad(img, max_size=max_size)
+        video_frame_crop.append(img)
+    save_video_from_cv2_list(video_frame_crop, save_path, fps=24.0, rgb2bgr=True)
+    return video_frame_crop
+
+def save_audio(ori_video_path, sub_task):
+    save_path = ori_video_path.replace('original_videos', 'processed/audio/')
+    save_dir = os.path.dirname(save_path)
+    save_path = save_path + '.wav'
+    if not os.path.exists(save_dir):
+        os.makedirs(save_dir)
+    ori_video_path = ori_video_path.replace(sub_task, sub_task+'_24fps')
+    audio_clip = AudioFileClip(ori_video_path)
+    audio_clip.write_audiofile(save_path)
+
+def draw_pose_video(pose_params_path, save_path, max_size, ori_frames=None):
+    pose_files = os.listdir(pose_params_path)
+     # 生成Pose图cd pro 
+    output_pose_img = []
+    for i in range(0, len(pose_files)):
+        pose_params_path_tmp = pose_params_path + '/' + str(i) + '.npy'
+        detected_pose = np.load(pose_params_path_tmp, allow_pickle=True).tolist()
+        imh_new, imw_new, rb, re, cb, ce = detected_pose['draw_pose_params']
+        im = draw_pose(detected_pose, imh_new, imw_new, ref_w=800)
+        im = np.transpose(np.array(im),(1,2,0))
+        img_new = np.zeros((max_size, max_size, 3)).astype('uint8')
+        img_new[rb:re,cb:ce,:] = im
+        if ori_frames is not None:
+            img_new = img_new * 0.6 + ori_frames[i] * 0.4
+            img_new = img_new.astype('uint8')
+        output_pose_img.append(img_new)
+
+    output_pose_img = np.stack(output_pose_img)
+    save_video_from_cv2_list(output_pose_img, save_path, fps=24.0, rgb2bgr=True)
+    print('save to ' + save_path)
+
+visualization = False
+for sub_task in tasks:
+
+    ori_list = os.listdir(base_dir+sub_task)[start:end]
+    
+    mp4_list = ori_list
+
+    new_dir = base_dir+sub_task+'_24fps'
+    if not os.path.exists(new_dir):
+        os.makedirs(new_dir)
+    index = 1
+    for i, mp4_file in enumerate(mp4_list):
+        ori_video_path = base_dir+sub_task+'/'+mp4_file
+        if ori_video_path[-3:]=='mp4' or ori_video_path[-3:] =='MOV':
+            try:
+                # 转换祯率
+                ori_video_path_new = ori_video_path.replace(sub_task, sub_task+'_24fps')
+                if '.MOV' in ori_video_path_new:
+                    ori_video_path_new.replace('.MOV', '.mp4')
+                convert_fps(ori_video_path, ori_video_path_new)
+                print([index+start, ori_video_path, start, end])
+                # 提取Pose
+                detected_poses, height, width, ori_frames = get_video_pose(ori_video_path_new, max_frame=None)
+                print(height, width)
+                # 提取相关参数
+                res_params = get_pose_params(detected_poses, MAX_SIZE)
+                # 存储Pose参数
+                save_pose_params(detected_poses, res_params['pose_params'], res_params['draw_pose_params'], ori_video_path)
+                # 存储截取视频
+                video_frame_crop = save_processed_video(ori_frames, res_params['video_params'], ori_video_path, MAX_SIZE)
+                # 存储音频
+                save_audio(ori_video_path, sub_task)
+                index += 1
+                if visualization:
+                    # 绘制pose图
+                    pose_params_path = ori_video_path.replace('original_videos', 'image_audio_features/pose')
+                    save_path = "./vis_pose_results/" + os.path.basename(ori_video_path)
+                    draw_pose_video(pose_params_path, save_path, ori_frames=video_frame_crop)
+            except:
+                print(["extract crash!", index+start, ori_video_path, start, end])
+                continue 
+
+    print(["All Finished", sub_task, start, end])

EMTD_dataset/slice.sh

@@ -0,0 +1,6 @@
+root=path_to_download_video_splits
+target=path_to_save_sliced_videos
+mkdir ${root}/${target}_segs
+for file in $(ls ${root}/${target}/); do
+  scenedetect --input ${root}/${target}/${file} --output ${root}/${target}_segs/ detect-content split-video
+done

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

ORIGINAL_README.md

@@ -0,0 +1,262 @@
+<h1 align='center'>EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation</h1>
+
+<div align='center'>
+    <a href='https://github.com/mengrang' target='_blank'>Rang Meng</a><sup></sup>&emsp;
+    <a href='https://github.com/' target='_blank'>Xingyu Zhang</a><sup></sup>&emsp;
+    <a href='https://lymhust.github.io/' target='_blank'>Yuming Li</a><sup></sup>&emsp;
+    <a href='https://github.com/' target='_blank'>Chenguang Ma</a><sup></sup>
+</div>
+
+
+<div align='center'>
+Terminal Technology Department, Alipay, Ant Group.
+</div>
+<br>
+<div align='center'>
+    <a href='https://antgroup.github.io/ai/echomimic_v2/'><img src='https://img.shields.io/badge/Project-Page-blue'></a>
+    <a href='https://huggingface.co/BadToBest/EchoMimicV2'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model-yellow'></a>
+    <!--<a href='https://antgroup.github.io/ai/echomimic_v2/'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Demo-yellow'></a>-->
+    <a href='https://modelscope.cn/models/BadToBest/EchoMimicV2'><img src='https://img.shields.io/badge/ModelScope-Model-purple'></a>
+    <!--<a href='https://antgroup.github.io/ai/echomimic_v2/'><img src='https://img.shields.io/badge/ModelScope-Demo-purple'></a>-->
+    <a href='https://arxiv.org/abs/2411.10061'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
+    <a href='https://github.com/antgroup/echomimic_v2/blob/main/assets/halfbody_demo/wechat_group.png'><img src='https://badges.aleen42.com/src/wechat.svg'></a>
+</div>
+<div align='center'>
+    <a href='https://github.com/antgroup/echomimic_v2/discussions/53'><img src='https://img.shields.io/badge/English-Common Problems-orange'></a>
+    <a href='https://github.com/antgroup/echomimic_v2/discussions/40'><img src='https://img.shields.io/badge/中文版-常见问题汇总-orange'></a>
+</div>
+
+## &#x1F680; EchoMimic Series
+* EchoMimicV1: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning. [GitHub](https://github.com/antgroup/echomimic)
+* EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation. [GitHub](https://github.com/antgroup/echomimic_v2)
+
+## &#x1F4E3; Updates
+* [2024.11.27] 🔥 Thanks [AiMotionStudio](https://www.youtube.com/@AiMotionStudio) for the [installation tutorial](https://www.youtube.com/watch?v=2ab6U1-nVTQ).
+* [2024.11.22] 🔥 [GradioUI](https://github.com/antgroup/echomimic_v2/blob/main/app.py) is now available. Thanks @gluttony-10 for the contribution.
+* [2024.11.22] 🔥 [ComfyUI](https://github.com/smthemex/ComfyUI_EchoMimic) is now available. Thanks @smthemex for the contribution.
+* [2024.11.21] 🔥 We release the EMTD dataset list and processing scripts.
+* [2024.11.21] 🔥 We release our [EchoMimicV2](https://github.com/antgroup/echomimic_v2) codes and models.
+* [2024.11.15] 🔥 Our [paper](https://arxiv.org/abs/2411.10061) is in public on arxiv.
+
+## &#x1F305; Gallery
+### Introduction
+<table class="center">
+<tr>
+    <td width=50% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/f544dfc0-7d1a-4c2c-83c0-608f28ffda25" muted="false"></video>
+    </td>
+    <td width=50% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/7f626b65-725c-4158-a96b-062539874c63" muted="false"></video>
+    </td>
+</tr>
+</table>
+
+### English Driven Audio
+<table class="center">
+<tr>
+    <td width=100% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/3d5ac52c-62e4-41bc-8b27-96f005bbd781" muted="false"></video>
+    </td>
+</tr>
+</table>
+<table class="center">
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/e8dd6919-665e-4343-931f-54c93dc49a7d" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/2a377391-a0d3-4a9d-8dde-cc59006e7e5b" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/462bf3bb-0af2-43e2-a2dc-559e79953f3c" muted="false"></video>
+    </td>
+</tr>
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/0e988e7f-6346-4b54-9061-9cfc7a80e9c8" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/56f739bd-afbf-4ed3-ab15-73a811c1bc46" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/1b2f7827-111d-4fc0-a773-e1731bba285d" muted="false"></video>
+    </td>
+</tr>
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/a76b6cc8-89b9-4f7e-b1ce-c85a657b6dc7" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/bf03b407-5033-4a30-aa59-b8680a515181" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/f98b3985-572c-499f-ae1a-1b9befe3086f" muted="false"></video>
+    </td>
+</tr>
+</table>
+
+### Chinese Driven Audio
+<table class="center">
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/a940a332-2fd1-48e7-b3c4-f88f63fd1c9d" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/8f185829-c67f-45f4-846c-fcbe012c3acf" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/a49ab9be-f17b-41c5-96dd-20dc8d759b45" muted="false"></video>
+    </td>
+</tr>
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/1136ec68-a13c-4ee7-ab31-5621530bf9df" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/fc16d512-8806-4662-ae07-8fcf45c75a83" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/f8559cd1-f555-4781-9251-dfcef10b5b01" muted="false"></video>
+    </td>
+</tr>
+<tr>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/c7473e3a-ab51-4ad5-be96-6c4691fc0c6e" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/ca69eac0-5126-41ee-8cac-c9722004d771" muted="false"></video>
+    </td>
+    <td width=30% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/e66f1712-b66d-46b5-8bbd-811fbcfea4fd" muted="false"></video>
+    </td>
+</tr>
+</table>
+
+## ⚒️ Installation
+### Download the Codes
+
+```bash
+  git clone https://github.com/antgroup/echomimic_v2
+  cd echomimic_v2
+```
+
+### Python Environment Setup
+
+- Tested System Environment: Centos 7.2/Ubuntu 22.04, Cuda >= 11.7
+- Tested GPUs: A100(80G) / RTX4090D (24G) / V100(16G)
+- Tested Python Version: 3.8 / 3.10 / 3.11
+
+Create conda environment (Recommended):
+
+```bash
+  conda create -n echomimic python=3.10
+  conda activate echomimic
+```
+
+Install packages with `pip`
+```bash
+  pip install pip -U
+  pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 xformers==0.0.28.post3 --index-url https://download.pytorch.org/whl/cu124
+  pip install torchao --index-url https://download.pytorch.org/whl/nightly/cu124
+  pip install -r requirements.txt
+  pip install --no-deps facenet_pytorch==2.6.0
+```
+
+### Download ffmpeg-static
+Download and decompress [ffmpeg-static](https://www.johnvansickle.com/ffmpeg/old-releases/ffmpeg-4.4-amd64-static.tar.xz), then
+```
+export FFMPEG_PATH=/path/to/ffmpeg-4.4-amd64-static
+```
+
+### Download pretrained weights
+
+```shell
+git lfs install
+git clone https://huggingface.co/BadToBest/EchoMimicV2 pretrained_weights
+```
+
+The **pretrained_weights** is organized as follows.
+
+```
+./pretrained_weights/
+├── denoising_unet.pth
+├── reference_unet.pth
+├── motion_module.pth
+├── pose_encoder.pth
+├── sd-vae-ft-mse
+│   └── ...
+├── sd-image-variations-diffusers
+│   └── ...
+└── audio_processor
+    └── tiny.pt
+```
+
+In which **denoising_unet.pth** / **reference_unet.pth** / **motion_module.pth** / **pose_encoder.pth** are the main checkpoints of **EchoMimic**. Other models in this hub can be also downloaded from it's original hub, thanks to their brilliant works:
+- [sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse)
+- [sd-image-variations-diffusers](https://huggingface.co/lambdalabs/sd-image-variations-diffusers)
+- [audio_processor(whisper)](https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt)
+
+### Inference on Demo 
+Run the gradio:
+```bash
+python app.py
+```
+Run the python inference script:
+```bash
+python infer.py --config='./configs/prompts/infer.yaml'
+```
+
+### EMTD Dataset
+Download dataset:
+```bash
+python ./EMTD_dataset/download.py
+```
+Slice dataset:
+```bash
+bash ./EMTD_dataset/slice.sh
+```
+Process dataset:
+```bash
+python ./EMTD_dataset/preprocess.py
+```
+
+## 📝 Release Plans
+
+|  Status  | Milestone                                                                | ETA |
+|:--------:|:-------------------------------------------------------------------------|:--:|
+|    ✅    | The inference source code of EchoMimicV2 meet everyone on GitHub   | 21st Nov, 2024 |
+|    ✅    | Pretrained models trained on English and Mandarin Chinese on HuggingFace | 21st Nov, 2024 |
+|    ✅    | Pretrained models trained on English and Mandarin Chinese on ModelScope   | 21st Nov, 2024 |
+|    ✅    | EMTD dataset list and processing scripts                | 21st Nov, 2024 |
+|    🚀    | Accelerated models to be released                                        | TBD |
+|    🚀    | Online Demo on ModelScope to be released            | TBD |
+|    🚀    | Online Demo on HuggingFace to be released         | TBD |
+
+## ⚖️ Disclaimer
+This project is intended for academic research, and we explicitly disclaim any responsibility for user-generated content. Users are solely liable for their actions while using the generative model. The project contributors have no legal affiliation with, nor accountability for, users' behaviors. It is imperative to use the generative model responsibly, adhering to both ethical and legal standards.
+
+## 🙏🏻 Acknowledgements
+
+We would like to thank the contributors to the [MimicMotion](https://github.com/Tencent/MimicMotion) and [Moore-AnimateAnyone](https://github.com/MooreThreads/Moore-AnimateAnyone) repositories, for their open research and exploration. 
+
+We are also grateful to [CyberHost](https://cyberhost.github.io/) and [Vlogger](https://enriccorona.github.io/vlogger/) for their outstanding work in the area of audio-driven human animation.
+
+If we missed any open-source projects or related articles, we would like to complement the acknowledgement of this specific work immediately.
+
+## &#x1F4D2; Citation
+
+If you find our work useful for your research, please consider citing the paper :
+
+```
+@misc{meng2024echomimic,
+  title={EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation},
+  author={Rang Meng, Xingyu Zhang, Yuming Li, Chenguang Ma},
+  year={2024},
+  eprint={2411.10061},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV}
+}
+```
+
+## &#x1F31F; Star History
+[![Star History Chart](https://api.star-history.com/svg?repos=antgroup/echomimic_v2&type=Date)](https://star-history.com/#antgroup/echomimic_v2&Date)

app.py

@@ -0,0 +1,277 @@
+import os
+import random
+from pathlib import Path
+import numpy as np
+import torch
+from diffusers import AutoencoderKL, DDIMScheduler
+from PIL import Image
+from src.models.unet_2d_condition import UNet2DConditionModel
+from src.models.unet_3d_emo import EMOUNet3DConditionModel
+from src.models.whisper.audio2feature import load_audio_model
+from src.pipelines.pipeline_echomimicv2 import EchoMimicV2Pipeline
+from src.utils.util import save_videos_grid
+from src.models.pose_encoder import PoseEncoder
+from src.utils.dwpose_util import draw_pose_select_v2
+from moviepy.editor import VideoFileClip, AudioFileClip
+
+import gradio as gr
+from datetime import datetime
+from torchao.quantization import quantize_, int8_weight_only
+import gc
+
+total_vram_in_gb = torch.cuda.get_device_properties(0).total_memory / 1073741824
+print(f'\033[32mCUDA版本：{torch.version.cuda}\033[0m')
+print(f'\033[32mPytorch版本：{torch.__version__}\033[0m')
+print(f'\033[32m显卡型号：{torch.cuda.get_device_name()}\033[0m')
+print(f'\033[32m显存大小：{total_vram_in_gb:.2f}GB\033[0m')
+print(f'\033[32m精度：float16\033[0m')
+dtype = torch.float16
+if torch.cuda.is_available():
+        device = "cuda"
+else:
+    print("cuda not available, using cpu")
+    device = "cpu"
+
+ffmpeg_path = os.getenv('FFMPEG_PATH')
+if ffmpeg_path is None:
+    print("please download ffmpeg-static and export to FFMPEG_PATH. \nFor example: export FFMPEG_PATH=./ffmpeg-4.4-amd64-static")
+elif ffmpeg_path not in os.getenv('PATH'):
+    print("add ffmpeg to path")
+    os.environ["PATH"] = f"{ffmpeg_path}:{os.environ['PATH']}"
+
+
+def generate(image_input, audio_input, pose_input, width, height, length, steps, sample_rate, cfg, fps, context_frames, context_overlap, quantization_input, seed):
+    gc.collect()
+    torch.cuda.empty_cache()
+    torch.cuda.ipc_collect()
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    save_dir = Path("outputs")
+    save_dir.mkdir(exist_ok=True, parents=True)
+
+    ############# model_init started #############
+    ## vae init
+    vae = AutoencoderKL.from_pretrained("./pretrained_weights/sd-vae-ft-mse").to(device, dtype=dtype)
+    if quantization_input:
+        quantize_(vae, int8_weight_only())
+        print("使用int8量化")
+
+    ## reference net init
+    reference_unet = UNet2DConditionModel.from_pretrained("./pretrained_weights/sd-image-variations-diffusers", subfolder="unet", use_safetensors=False).to(dtype=dtype, device=device)
+    reference_unet.load_state_dict(torch.load("./pretrained_weights/reference_unet.pth", weights_only=True))
+    if quantization_input:
+        quantize_(reference_unet, int8_weight_only())
+
+    ## denoising net init
+    if os.path.exists("./pretrained_weights/motion_module.pth"):
+        print('using motion module')
+    else:
+        exit("motion module not found")
+        ### stage1 + stage2
+    denoising_unet = EMOUNet3DConditionModel.from_pretrained_2d(
+        "./pretrained_weights/sd-image-variations-diffusers",
+        "./pretrained_weights/motion_module.pth",
+        subfolder="unet",
+        unet_additional_kwargs = {
+            "use_inflated_groupnorm": True,
+            "unet_use_cross_frame_attention": False,
+            "unet_use_temporal_attention": False,
+            "use_motion_module": True,
+            "cross_attention_dim": 384,
+            "motion_module_resolutions": [
+                1,
+                2,
+                4,
+                8
+            ],
+            "motion_module_mid_block": True ,
+            "motion_module_decoder_only": False,
+            "motion_module_type": "Vanilla",
+            "motion_module_kwargs":{
+                "num_attention_heads": 8,
+                "num_transformer_block": 1,
+                "attention_block_types": [
+                    'Temporal_Self',
+                    'Temporal_Self'
+                ],
+                "temporal_position_encoding": True,
+                "temporal_position_encoding_max_len": 32,
+                "temporal_attention_dim_div": 1,
+            }
+        },
+    ).to(dtype=dtype, device=device)
+    denoising_unet.load_state_dict(torch.load("./pretrained_weights/denoising_unet.pth", weights_only=True),strict=False)
+
+    # pose net init
+    pose_net = PoseEncoder(320, conditioning_channels=3, block_out_channels=(16, 32, 96, 256)).to(dtype=dtype, device=device)
+    pose_net.load_state_dict(torch.load("./pretrained_weights/pose_encoder.pth", weights_only=True))
+
+    ### load audio processor params
+    audio_processor = load_audio_model(model_path="./pretrained_weights/audio_processor/tiny.pt", device=device)
+   
+    ############# model_init finished #############
+    sched_kwargs = {
+        "beta_start": 0.00085,
+        "beta_end": 0.012,
+        "beta_schedule": "linear",
+        "clip_sample": False,
+        "steps_offset": 1,
+        "prediction_type": "v_prediction",
+        "rescale_betas_zero_snr": True,
+        "timestep_spacing": "trailing"
+    }
+    scheduler = DDIMScheduler(**sched_kwargs)
+
+    pipe = EchoMimicV2Pipeline(
+        vae=vae,
+        reference_unet=reference_unet,
+        denoising_unet=denoising_unet,
+        audio_guider=audio_processor,
+        pose_encoder=pose_net,
+        scheduler=scheduler,
+    )
+
+    pipe = pipe.to(device, dtype=dtype)
+
+    if seed is not None and seed > -1:
+        generator = torch.manual_seed(seed)
+    else:
+        seed = random.randint(100, 1000000)
+        generator = torch.manual_seed(seed)
+
+    inputs_dict = {
+        "refimg": image_input,
+        "audio": audio_input,
+        "pose": pose_input,
+    }
+
+    print('Pose:', inputs_dict['pose'])
+    print('Reference:', inputs_dict['refimg'])
+    print('Audio:', inputs_dict['audio'])
+
+    save_name = f"{save_dir}/{timestamp}"
+    
+    ref_image_pil = Image.open(inputs_dict['refimg']).resize((width, height))
+    audio_clip = AudioFileClip(inputs_dict['audio'])
+    
+    length = min(length, int(audio_clip.duration * fps), len(os.listdir(inputs_dict['pose'])))
+
+    start_idx = 0
+
+    pose_list = []
+    for index in range(start_idx, start_idx + length):
+        tgt_musk = np.zeros((width, height, 3)).astype('uint8')
+        tgt_musk_path = os.path.join(inputs_dict['pose'], "{}.npy".format(index))
+        detected_pose = np.load(tgt_musk_path, allow_pickle=True).tolist()
+        imh_new, imw_new, rb, re, cb, ce = detected_pose['draw_pose_params']
+        im = draw_pose_select_v2(detected_pose, imh_new, imw_new, ref_w=800)
+        im = np.transpose(np.array(im),(1, 2, 0))
+        tgt_musk[rb:re,cb:ce,:] = im
+
+        tgt_musk_pil = Image.fromarray(np.array(tgt_musk)).convert('RGB')
+        pose_list.append(torch.Tensor(np.array(tgt_musk_pil)).to(dtype=dtype, device=device).permute(2,0,1) / 255.0)
+    
+    poses_tensor = torch.stack(pose_list, dim=1).unsqueeze(0)
+    audio_clip = AudioFileClip(inputs_dict['audio'])
+    
+    audio_clip = audio_clip.set_duration(length / fps)
+    video = pipe(
+        ref_image_pil,
+        inputs_dict['audio'],
+        poses_tensor[:,:,:length,...],
+        width,
+        height,
+        length,
+        steps,
+        cfg,
+        generator=generator,
+        audio_sample_rate=sample_rate,
+        context_frames=context_frames,
+        fps=fps,
+        context_overlap=context_overlap,
+        start_idx=start_idx,
+    ).videos 
+    
+    final_length = min(video.shape[2], poses_tensor.shape[2], length)
+    video_sig = video[:, :, :final_length, :, :]
+    
+    save_videos_grid(
+        video_sig,
+        save_name + "_woa_sig.mp4",
+        n_rows=1,
+        fps=fps,
+    )
+
+    video_clip_sig = VideoFileClip(save_name + "_woa_sig.mp4",)
+    video_clip_sig = video_clip_sig.set_audio(audio_clip)
+    video_clip_sig.write_videofile(save_name + "_sig.mp4", codec="libx264", audio_codec="aac", threads=2)
+    video_output = save_name + "_sig.mp4"
+    seed_text = gr.update(visible=True, value=seed)
+    return video_output, seed_text
+
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+            <div>
+                <h2 style="font-size: 30px;text-align: center;">EchoMimicV2</h2>
+            </div>
+            <div style="text-align: center;">
+                <a href="https://github.com/antgroup/echomimic_v2">🌐 Github</a> |
+                <a href="https://arxiv.org/abs/2411.10061">📜 arXiv </a>
+            </div>
+            <div style="text-align: center; font-weight: bold; color: red;">
+                ⚠️ 该演示仅供学术研究和体验使用。
+            </div>
+            
+            """)
+    with gr.Column():
+        with gr.Row():
+            with gr.Column():
+                with gr.Group():
+                    image_input = gr.Image(label="图像输入（自动缩放）", type="filepath")
+                    audio_input = gr.Audio(label="音频输入", type="filepath")
+                    pose_input = gr.Textbox(label="姿态输入（目录地址）", placeholder="请输入姿态数据的目录地址", value="assets/halfbody_demo/pose/01")
+                with gr.Group():
+                    with gr.Row():
+                        width = gr.Number(label="宽度（16的倍数，推荐768）", value=768)
+                        height = gr.Number(label="高度（16的倍数，推荐768）", value=768)
+                        length = gr.Number(label="视频长度，推荐240）", value=240)
+                    with gr.Row():
+                        steps = gr.Number(label="步骤（推荐30）", value=20)
+                        sample_rate = gr.Number(label="采样率（推荐16000）", value=16000)
+                        cfg = gr.Number(label="cfg（推荐2.5）", value=2.5, step=0.1)
+                    with gr.Row():
+                        fps = gr.Number(label="帧率（推荐24）", value=24)
+                        context_frames = gr.Number(label="上下文框架（推荐12）", value=12)
+                        context_overlap = gr.Number(label="上下文重叠（推荐3）", value=3)
+                    with gr.Row():
+                        quantization_input = gr.Checkbox(label="int8量化（推荐显存12G的用户开启，并使用不超过5秒的音频）", value=False)
+                        seed = gr.Number(label="种子(-1为随机)", value=-1)
+                generate_button = gr.Button("🎬 生成视频")
+            with gr.Column():
+                video_output = gr.Video(label="输出视频")
+                seed_text = gr.Textbox(label="种子", interactive=False, visible=False)
+        gr.Examples(
+            examples=[
+                ["EMTD_dataset/ref_imgs_by_FLUX/man/0001.png", "assets/halfbody_demo/audio/chinese/echomimicv2_man.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/woman/0077.png", "assets/halfbody_demo/audio/chinese/echomimicv2_woman.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/man/0003.png", "assets/halfbody_demo/audio/chinese/fighting.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/woman/0033.png", "assets/halfbody_demo/audio/chinese/good.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/man/0010.png", "assets/halfbody_demo/audio/chinese/news.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/man/1168.png", "assets/halfbody_demo/audio/chinese/no_smoking.wav"],
+                ["EMTD_dataset/ref_imgs_by_FLUX/woman/0057.png", "assets/halfbody_demo/audio/chinese/ultraman.wav"]
+            ],
+            inputs=[image_input, audio_input],  
+            label="预设人物及音频",
+        )
+
+    generate_button.click(
+        generate,
+        inputs=[image_input, audio_input, pose_input, width, height, length, steps, sample_rate, cfg, fps, context_frames, context_overlap, quantization_input, seed],
+        outputs=[video_output, seed_text],
+    )
+
+
+
+if __name__ == "__main__":
+    demo.queue()
+    demo.launch(inbrowser=True)

assets/halfbody_demo/audio/chinese/echomimicv2_woman.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c828b9587a441881cbf5275c4ea65ed2a893129c585759c582a2e2e7e86718
+size 1096748