forked from huggingface/diffusers
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathexport_utils.py
More file actions
272 lines (222 loc) 路 9.53 KB
/
Copy pathexport_utils.py
File metadata and controls
272 lines (222 loc) 路 9.53 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
import io
import os
import random
import shutil
import struct
import subprocess
import tempfile
from contextlib import contextmanager
from typing import List, Optional, Union
import numpy as np
import PIL.Image
import PIL.ImageOps
from .import_utils import BACKENDS_MAPPING, is_imageio_available, is_opencv_available
from .logging import get_logger
global_rng = random.Random()
logger = get_logger(__name__)
@contextmanager
def buffered_writer(raw_f):
f = io.BufferedWriter(raw_f)
yield f
f.flush()
def export_to_gif(image: List[PIL.Image.Image], output_gif_path: str = None, fps: int = 10) -> str:
if output_gif_path is None:
output_gif_path = tempfile.NamedTemporaryFile(suffix=".gif").name
image[0].save(
output_gif_path,
save_all=True,
append_images=image[1:],
optimize=False,
duration=1000 // fps,
loop=0,
)
return output_gif_path
def export_to_ply(mesh, output_ply_path: str = None):
"""
Write a PLY file for a mesh.
"""
if output_ply_path is None:
output_ply_path = tempfile.NamedTemporaryFile(suffix=".ply").name
coords = mesh.verts.detach().cpu().numpy()
faces = mesh.faces.cpu().numpy()
rgb = np.stack([mesh.vertex_channels[x].detach().cpu().numpy() for x in "RGB"], axis=1)
with buffered_writer(open(output_ply_path, "wb")) as f:
f.write(b"ply\n")
f.write(b"format binary_little_endian 1.0\n")
f.write(bytes(f"element vertex {len(coords)}\n", "ascii"))
f.write(b"property float x\n")
f.write(b"property float y\n")
f.write(b"property float z\n")
if rgb is not None:
f.write(b"property uchar red\n")
f.write(b"property uchar green\n")
f.write(b"property uchar blue\n")
if faces is not None:
f.write(bytes(f"element face {len(faces)}\n", "ascii"))
f.write(b"property list uchar int vertex_index\n")
f.write(b"end_header\n")
if rgb is not None:
rgb = (rgb * 255.499).round().astype(int)
vertices = [
(*coord, *rgb)
for coord, rgb in zip(
coords.tolist(),
rgb.tolist(),
)
]
format = struct.Struct("<3f3B")
for item in vertices:
f.write(format.pack(*item))
else:
format = struct.Struct("<3f")
for vertex in coords.tolist():
f.write(format.pack(*vertex))
if faces is not None:
format = struct.Struct("<B3I")
for tri in faces.tolist():
f.write(format.pack(len(tri), *tri))
return output_ply_path
def export_to_obj(mesh, output_obj_path: str = None):
if output_obj_path is None:
output_obj_path = tempfile.NamedTemporaryFile(suffix=".obj").name
verts = mesh.verts.detach().cpu().numpy()
faces = mesh.faces.cpu().numpy()
vertex_colors = np.stack([mesh.vertex_channels[x].detach().cpu().numpy() for x in "RGB"], axis=1)
vertices = [
"{} {} {} {} {} {}".format(*coord, *color) for coord, color in zip(verts.tolist(), vertex_colors.tolist())
]
faces = ["f {} {} {}".format(str(tri[0] + 1), str(tri[1] + 1), str(tri[2] + 1)) for tri in faces.tolist()]
combined_data = ["v " + vertex for vertex in vertices] + faces
with open(output_obj_path, "w") as f:
f.writelines("\n".join(combined_data))
def _legacy_export_to_video(
video_frames: Union[List[np.ndarray], List[PIL.Image.Image]], output_video_path: str = None, fps: int = 10
):
if is_opencv_available():
import cv2
else:
raise ImportError(BACKENDS_MAPPING["opencv"][1].format("export_to_video"))
if output_video_path is None:
output_video_path = tempfile.NamedTemporaryFile(suffix=".mp4").name
if isinstance(video_frames[0], np.ndarray):
video_frames = [(frame * 255).astype(np.uint8) for frame in video_frames]
elif isinstance(video_frames[0], PIL.Image.Image):
video_frames = [np.array(frame) for frame in video_frames]
fourcc = cv2.VideoWriter_fourcc(*"mp4v")
h, w, c = video_frames[0].shape
video_writer = cv2.VideoWriter(output_video_path, fourcc, fps=fps, frameSize=(w, h))
for i in range(len(video_frames)):
img = cv2.cvtColor(video_frames[i], cv2.COLOR_RGB2BGR)
video_writer.write(img)
return output_video_path
def export_to_video(
video_frames: Union[List[np.ndarray], List[PIL.Image.Image]],
output_video_path: str = None,
fps: int = 10,
quality: float = 5.0,
bitrate: Optional[int] = None,
macro_block_size: Optional[int] = 16,
) -> str:
"""
quality:
Video output quality. Default is 5. Uses variable bit rate. Highest quality is 10, lowest is 0. Set to None to
prevent variable bitrate flags to FFMPEG so you can manually specify them using output_params instead.
Specifying a fixed bitrate using `bitrate` disables this parameter.
bitrate:
Set a constant bitrate for the video encoding. Default is None causing `quality` parameter to be used instead.
Better quality videos with smaller file sizes will result from using the `quality` variable bitrate parameter
rather than specifying a fixed bitrate with this parameter.
macro_block_size:
Size constraint for video. Width and height, must be divisible by this number. If not divisible by this number
imageio will tell ffmpeg to scale the image up to the next closest size divisible by this number. Most codecs
are compatible with a macroblock size of 16 (default), some can go smaller (4, 8). To disable this automatic
feature set it to None or 1, however be warned many players can't decode videos that are odd in size and some
codecs will produce poor results or fail. See https://en.wikipedia.org/wiki/Macroblock.
"""
# TODO: Dhruv. Remove by Diffusers release 0.33.0
# Added to prevent breaking existing code
if not is_imageio_available():
logger.warning(
(
"It is recommended to use `export_to_video` with `imageio` and `imageio-ffmpeg` as a backend. \n"
"These libraries are not present in your environment. Attempting to use legacy OpenCV backend to export video. \n"
"Support for the OpenCV backend will be deprecated in a future Diffusers version"
)
)
return _legacy_export_to_video(video_frames, output_video_path, fps)
if is_imageio_available():
import imageio
else:
raise ImportError(BACKENDS_MAPPING["imageio"][1].format("export_to_video"))
try:
imageio.plugins.ffmpeg.get_exe()
except AttributeError:
raise AttributeError(
(
"Found an existing imageio backend in your environment. Attempting to export video with imageio. \n"
"Unable to find a compatible ffmpeg installation in your environment to use with imageio. Please install via `pip install imageio-ffmpeg"
)
)
if output_video_path is None:
output_video_path = tempfile.NamedTemporaryFile(suffix=".mp4").name
if isinstance(video_frames[0], np.ndarray):
video_frames = [(frame * 255).astype(np.uint8) for frame in video_frames]
elif isinstance(video_frames[0], PIL.Image.Image):
video_frames = [np.array(frame) for frame in video_frames]
with imageio.get_writer(
output_video_path, fps=fps, quality=quality, bitrate=bitrate, macro_block_size=macro_block_size
) as writer:
for frame in video_frames:
writer.append_data(frame)
return output_video_path
def export_to_merged_video_audio(video_path: str, audio_path: str):
"""
Merge the video and audio into a new video, with the duration set to the shorter of the two, and overwrite the
original video file.
Parameters:
video_path (str): Path to the original video file
audio_path (str): Path to the audio file
"""
if not os.path.exists(video_path):
raise FileNotFoundError(f"video file {video_path} does not exist")
if not os.path.exists(audio_path):
raise FileNotFoundError(f"audio file {audio_path} does not exist")
base, ext = os.path.splitext(video_path)
temp_output = f"{base}_temp{ext}"
try:
# Create ffmpeg command
command = [
"ffmpeg",
"-y", # overwrite
"-i",
video_path,
"-i",
audio_path,
"-c:v",
"copy", # copy video stream
"-c:a",
"aac", # use AAC audio encoder
"-b:a",
"192k", # set audio bitrate (optional)
"-map",
"0:v:0", # select the first video stream
"-map",
"1:a:0", # select the first audio stream
"-shortest", # choose the shortest duration
temp_output,
]
# Execute the command
logger.info("Start merging video and audio...")
result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
# Check result
if result.returncode != 0:
error_msg = f"FFmpeg execute failed: {result.stderr}"
logger.error(error_msg)
raise RuntimeError(error_msg)
shutil.move(temp_output, video_path)
logger.info(f"Merge completed, saved to {video_path}")
except Exception as e:
if os.path.exists(temp_output):
os.remove(temp_output)
logger.error(f"merge_video_audio failed with error: {e}")
raise