hzhang/MoneyPrinterTurbo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: support custom subtitle positioning

Browse Source
This commit is contained in:
yyhhyyyyyy
2024-07-24 14:25:20 +08:00
parent e64041c93d
commit e8b20c697d
9 changed files with 382 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
app/models/schema.py
View File

@@ -119,6 +119,7 @@ class VideoParams(BaseModel):
subtitle_enabled: Optional[bool] = True
subtitle_position: Optional[str] = "bottom" # top, bottom, center
custom_position: float = 70.0
font_name: Optional[str] = "STHeitiMedium.ttc"
text_fore_color: Optional[str] = "#FFFFFF"
text_background_color: Optional[str] = "transparent"

3
app/router.py
View File

@@ -6,9 +6,10 @@ Resources:
1. https://fastapi.tiangolo.com/tutorial/bigger-applications
"""
from fastapi import APIRouter
from app.controllers.v1 import video, llm
from app.controllers.v1 import llm, video
root_api_router = APIRouter()
# v1

147
app/services/video.py
View File

@@ -1,13 +1,14 @@
import glob
import random
from typing import List
from PIL import ImageFont, Image
from loguru import logger
from moviepy.editor import *
from moviepy.video.tools.subtitles import SubtitlesClip
from PIL import ImageFont
from app.models import const
from app.models.schema import VideoAspect, VideoParams, VideoConcatMode, MaterialInfo
from app.models.schema import MaterialInfo, VideoAspect, VideoConcatMode, VideoParams
from app.utils import utils
@@ -27,14 +28,15 @@ def get_bgm_file(bgm_type: str = "random", bgm_file: str = ""):
return ""
def combine_videos(combined_video_path: str,
video_paths: List[str],
audio_file: str,
video_aspect: VideoAspect = VideoAspect.portrait,
video_concat_mode: VideoConcatMode = VideoConcatMode.random,
max_clip_duration: int = 5,
threads: int = 2,
) -> str:
def combine_videos(
combined_video_path: str,
video_paths: List[str],
audio_file: str,
video_aspect: VideoAspect = VideoAspect.portrait,
video_concat_mode: VideoConcatMode = VideoConcatMode.random,
max_clip_duration: int = 5,
threads: int = 2,
) -> str:
audio_clip = AudioFileClip(audio_file)
audio_duration = audio_clip.duration
logger.info(f"max duration of audio: {audio_duration} seconds")
@@ -102,13 +104,19 @@ def combine_videos(combined_video_path: str,
new_height = int(clip_h * scale_factor)
clip_resized = clip.resize(newsize=(new_width, new_height))
background = ColorClip(size=(video_width, video_height), color=(0, 0, 0))
clip = CompositeVideoClip([
background.set_duration(clip.duration),
clip_resized.set_position("center")
])
background = ColorClip(
size=(video_width, video_height), color=(0, 0, 0)
)
clip = CompositeVideoClip(
[
background.set_duration(clip.duration),
clip_resized.set_position("center"),
]
)
logger.info(f"resizing video to {video_width} x {video_height}, clip size: {clip_w} x {clip_h}")
logger.info(
f"resizing video to {video_width} x {video_height}, clip size: {clip_w} x {clip_h}"
)
if clip.duration > max_clip_duration:
clip = clip.subclip(0, max_clip_duration)
@@ -118,21 +126,22 @@ def combine_videos(combined_video_path: str,
video_clip = concatenate_videoclips(clips)
video_clip = video_clip.set_fps(30)
logger.info(f"writing")
logger.info("writing")
# https://github.com/harry0703/MoneyPrinterTurbo/issues/111#issuecomment-2032354030
video_clip.write_videofile(filename=combined_video_path,
threads=threads,
logger=None,
temp_audiofile_path=output_dir,
audio_codec="aac",
fps=30,
)
video_clip.write_videofile(
filename=combined_video_path,
threads=threads,
logger=None,
temp_audiofile_path=output_dir,
audio_codec="aac",
fps=30,
)
video_clip.close()
logger.success(f"completed")
logger.success("completed")
return combined_video_path
def wrap_text(text, max_width, font='Arial', fontsize=60):
def wrap_text(text, max_width, font="Arial", fontsize=60):
# 创建字体对象
font = ImageFont.truetype(font, fontsize)
@@ -151,7 +160,7 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
_wrapped_lines_ = []
words = text.split(" ")
_txt_ = ''
_txt_ = ""
for word in words:
_before = _txt_
_txt_ += f"{word} "
@@ -167,14 +176,14 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
_wrapped_lines_.append(_txt_)
if processed:
_wrapped_lines_ = [line.strip() for line in _wrapped_lines_]
result = '\n'.join(_wrapped_lines_).strip()
result = "\n".join(_wrapped_lines_).strip()
height = len(_wrapped_lines_) * height
# logger.warning(f"wrapped text: {result}")
return result, height
_wrapped_lines_ = []
chars = list(text)
_txt_ = ''
_txt_ = ""
for word in chars:
_txt_ += word
_width, _height = get_text_size(_txt_)
@@ -182,20 +191,21 @@ def wrap_text(text, max_width, font='Arial', fontsize=60):
continue
else:
_wrapped_lines_.append(_txt_)
_txt_ = ''
_txt_ = ""
_wrapped_lines_.append(_txt_)
result = '\n'.join(_wrapped_lines_).strip()
result = "\n".join(_wrapped_lines_).strip()
height = len(_wrapped_lines_) * height
# logger.warning(f"wrapped text: {result}")
return result, height
def generate_video(video_path: str,
audio_path: str,
subtitle_path: str,
output_file: str,
params: VideoParams,
):
def generate_video(
video_path: str,
audio_path: str,
subtitle_path: str,
output_file: str,
params: VideoParams,
):
aspect = VideoAspect(params.video_aspect)
video_width, video_height = aspect.to_resolution()
@@ -215,7 +225,7 @@ def generate_video(video_path: str,
if not params.font_name:
params.font_name = "STHeitiMedium.ttc"
font_path = os.path.join(utils.font_dir(), params.font_name)
if os.name == 'nt':
if os.name == "nt":
font_path = font_path.replace("\\", "/")
logger.info(f"using font: {font_path}")
@@ -223,11 +233,9 @@ def generate_video(video_path: str,
def create_text_clip(subtitle_item):
phrase = subtitle_item[1]
max_width = video_width * 0.9
wrapped_txt, txt_height = wrap_text(phrase,
max_width=max_width,
font=font_path,
fontsize=params.font_size
)
wrapped_txt, txt_height = wrap_text(
phrase, max_width=max_width, font=font_path, fontsize=params.font_size
)
_clip = TextClip(
wrapped_txt,
font=font_path,
@@ -243,18 +251,26 @@ def generate_video(video_path: str,
_clip = _clip.set_end(subtitle_item[0][1])
_clip = _clip.set_duration(duration)
if params.subtitle_position == "bottom":
_clip = _clip.set_position(('center', video_height * 0.95 - _clip.h))
_clip = _clip.set_position(("center", video_height * 0.95 - _clip.h))
elif params.subtitle_position == "top":
_clip = _clip.set_position(('center', video_height * 0.1))
else:
_clip = _clip.set_position(('center', 'center'))
_clip = _clip.set_position(("center", video_height * 0.05))
elif params.subtitle_position == "custom":
# 确保字幕完全在屏幕内
margin = 10 # 额外的边距，单位为像素
max_y = video_height - _clip.h - margin
min_y = margin
custom_y = (video_height - _clip.h) * (params.custom_position / 100)
custom_y = max(min_y, min(custom_y, max_y)) # 限制 y 值在有效范围内
_clip = _clip.set_position(("center", custom_y))
else: # center
_clip = _clip.set_position(("center", "center"))
return _clip
video_clip = VideoFileClip(video_path)
audio_clip = AudioFileClip(audio_path).volumex(params.voice_volume)
if subtitle_path and os.path.exists(subtitle_path):
sub = SubtitlesClip(subtitles=subtitle_path, encoding='utf-8')
sub = SubtitlesClip(subtitles=subtitle_path, encoding="utf-8")
text_clips = []
for item in sub.subtitles:
clip = create_text_clip(subtitle_item=item)
@@ -264,24 +280,25 @@ def generate_video(video_path: str,
bgm_file = get_bgm_file(bgm_type=params.bgm_type, bgm_file=params.bgm_file)
if bgm_file:
try:
bgm_clip = (AudioFileClip(bgm_file)
.volumex(params.bgm_volume)
.audio_fadeout(3))
bgm_clip = (
AudioFileClip(bgm_file).volumex(params.bgm_volume).audio_fadeout(3)
)
bgm_clip = afx.audio_loop(bgm_clip, duration=video_clip.duration)
audio_clip = CompositeAudioClip([audio_clip, bgm_clip])
except Exception as e:
logger.error(f"failed to add bgm: {str(e)}")
video_clip = video_clip.set_audio(audio_clip)
video_clip.write_videofile(output_file,
audio_codec="aac",
temp_audiofile_path=output_dir,
threads=params.n_threads or 2,
logger=None,
fps=30,
)
video_clip.write_videofile(
output_file,
audio_codec="aac",
temp_audiofile_path=output_dir,
threads=params.n_threads or 2,
logger=None,
fps=30,
)
video_clip.close()
logger.success(f"completed")
logger.success("completed")
def preprocess_video(materials: List[MaterialInfo], clip_duration=4):
@@ -292,7 +309,7 @@ def preprocess_video(materials: List[MaterialInfo], clip_duration=4):
ext = utils.parse_extension(material.url)
try:
clip = VideoFileClip(material.url)
except Exception as e:
except Exception:
clip = ImageClip(material.url)
width = clip.size[0]
@@ -304,12 +321,18 @@ def preprocess_video(materials: List[MaterialInfo], clip_duration=4):
if ext in const.FILE_TYPE_IMAGES:
logger.info(f"processing image: {material.url}")
# 创建一个图片剪辑，并设置持续时间为3秒钟
clip = ImageClip(material.url).set_duration(clip_duration).set_position("center")
clip = (
ImageClip(material.url)
.set_duration(clip_duration)
.set_position("center")
)
# 使用resize方法来添加缩放效果。这里使用了lambda函数来使得缩放效果随时间变化。
# 假设我们想要从原始大小逐渐放大到120%的大小。
# t代表当前时间，clip.duration为视频总时长，这里是3秒。
# 注意：1 表示100%的大小，所以1.2表示120%的大小
zoom_clip = clip.resize(lambda t: 1 + (clip_duration * 0.03) * (t / clip.duration))
zoom_clip = clip.resize(
lambda t: 1 + (clip_duration * 0.03) * (t / clip.duration)
)
# 如果需要，可以创建一个包含缩放剪辑的复合视频剪辑
# （这在您想要在视频中添加其他元素时非常有用）