File size: 7,110 Bytes
69e1a8d | 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 | # Copyright 2025 The Lightricks team and The HuggingFace Team.
# All rights reserved.
#
# 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.
from collections.abc import Iterator
from fractions import Fraction
from itertools import chain
import numpy as np
import PIL.Image
import torch
from tqdm import tqdm
from ...utils import get_logger, is_av_available
logger = get_logger(__name__) # pylint: disable=invalid-name
_CAN_USE_AV = is_av_available()
if _CAN_USE_AV:
import av
else:
raise ImportError(
"PyAV is required to use LTX 2.0 video export utilities. You can install it with `pip install av`"
)
def _prepare_audio_stream(container: av.container.Container, audio_sample_rate: int) -> av.audio.AudioStream:
"""
Prepare the audio stream for writing.
"""
audio_stream = container.add_stream("aac", rate=audio_sample_rate)
audio_stream.codec_context.sample_rate = audio_sample_rate
audio_stream.codec_context.layout = "stereo"
audio_stream.codec_context.time_base = Fraction(1, audio_sample_rate)
return audio_stream
def _resample_audio(
container: av.container.Container, audio_stream: av.audio.AudioStream, frame_in: av.AudioFrame
) -> None:
cc = audio_stream.codec_context
# Use the encoder's format/layout/rate as the *target*
target_format = cc.format or "fltp" # AAC → usually fltp
target_layout = cc.layout or "stereo"
target_rate = cc.sample_rate or frame_in.sample_rate
audio_resampler = av.audio.resampler.AudioResampler(
format=target_format,
layout=target_layout,
rate=target_rate,
)
audio_next_pts = 0
for rframe in audio_resampler.resample(frame_in):
if rframe.pts is None:
rframe.pts = audio_next_pts
audio_next_pts += rframe.samples
rframe.sample_rate = frame_in.sample_rate
container.mux(audio_stream.encode(rframe))
# flush audio encoder
for packet in audio_stream.encode():
container.mux(packet)
def _write_audio(
container: av.container.Container,
audio_stream: av.audio.AudioStream,
samples: torch.Tensor,
audio_sample_rate: int,
) -> None:
if samples.ndim == 1:
samples = samples[:, None]
if samples.shape[1] != 2 and samples.shape[0] == 2:
samples = samples.T
if samples.shape[1] != 2:
raise ValueError(f"Expected samples with 2 channels; got shape {samples.shape}.")
# Convert to int16 packed for ingestion; resampler converts to encoder fmt.
if samples.dtype != torch.int16:
samples = torch.clip(samples, -1.0, 1.0)
samples = (samples * 32767.0).to(torch.int16)
frame_in = av.AudioFrame.from_ndarray(
samples.contiguous().reshape(1, -1).cpu().numpy(),
format="s16",
layout="stereo",
)
frame_in.sample_rate = audio_sample_rate
_resample_audio(container, audio_stream, frame_in)
def encode_video(
video: list[PIL.Image.Image] | np.ndarray | torch.Tensor | Iterator[torch.Tensor],
fps: int,
audio: torch.Tensor,
audio_sample_rate: int,
output_path: str,
video_chunks_number: int = 1,
) -> None:
"""
Encodes a video with audio using the PyAV library. Based on code from the original LTX-2 repo:
https://github.com/Lightricks/LTX-2/blob/4f410820b198e05074a1e92de793e3b59e9ab5a0/packages/ltx-pipelines/src/ltx_pipelines/utils/media_io.py#L182
Args:
video (`List[PIL.Image.Image]` or `np.ndarray` or `torch.Tensor`):
A video tensor of shape [frames, height, width, channels] with integer pixel values in [0, 255]. If the
input is a `np.ndarray`, it is expected to be a float array with values in [0, 1] (which is what pipelines
usually return with `output_type="np"`).
fps (`int`)
The frames per second (FPS) of the encoded video.
audio (`torch.Tensor`, *optional*):
An audio waveform of shape [audio_channels, samples].
audio_sample_rate: (`int`, *optional*):
The sampling rate of the audio waveform. For LTX 2, this is typically 24000 (24 kHz).
output_path (`str`):
The path to save the encoded video to.
video_chunks_number (`int`, *optional*, defaults to `1`):
The number of chunks to split the video into for encoding. Each chunk will be encoded separately. The
number of chunks to use often depends on the tiling config for the video VAE.
"""
if isinstance(video, list) and isinstance(video[0], PIL.Image.Image):
# Pipeline output_type="pil"; assumes each image is in "RGB" mode
video_frames = [np.array(frame) for frame in video]
video = np.stack(video_frames, axis=0)
video = torch.from_numpy(video)
elif isinstance(video, np.ndarray):
# Pipeline output_type="np"
is_denormalized = np.logical_and(np.zeros_like(video) <= video, video <= np.ones_like(video))
if np.all(is_denormalized):
video = (video * 255).round().astype("uint8")
else:
logger.warning(
"Supplied `numpy.ndarray` does not have values in [0, 1]. The values will be assumed to be pixel "
"values in [0, ..., 255] and will be used as is."
)
video = torch.from_numpy(video)
if isinstance(video, torch.Tensor):
# Split into video_chunks_number along the frame dimension
video = torch.tensor_split(video, video_chunks_number, dim=0)
video = iter(video)
first_chunk = next(video)
_, height, width, _ = first_chunk.shape
container = av.open(output_path, mode="w")
stream = container.add_stream("libx264", rate=int(fps))
stream.width = width
stream.height = height
stream.pix_fmt = "yuv420p"
if audio is not None:
if audio_sample_rate is None:
raise ValueError("audio_sample_rate is required when audio is provided")
audio_stream = _prepare_audio_stream(container, audio_sample_rate)
for video_chunk in tqdm(chain([first_chunk], video), total=video_chunks_number, desc="Encoding video chunks"):
video_chunk_cpu = video_chunk.to("cpu").numpy()
for frame_array in video_chunk_cpu:
frame = av.VideoFrame.from_ndarray(frame_array, format="rgb24")
for packet in stream.encode(frame):
container.mux(packet)
# Flush encoder
for packet in stream.encode():
container.mux(packet)
if audio is not None:
_write_audio(container, audio_stream, audio, audio_sample_rate)
container.close()
|