I have a python script, that generates a ffmpeg command for creating a slideshow with the "Ken Burns" filter.
For example, I have 10 images and want to create an 1-minute video at 30 FPS. It generates the following command:
/usr/local/bin/ffmpeg -i /Users/user/src/python/VideoMaker2/input/images/test/1.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/2.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/3.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/4.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/5.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/6.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/7.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/8.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/9.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/10.jpg -r 30 -t 60 -vcodec libx264 -preset ultrafast -tune zerolatency -pix_fmt yuv420p -filter_complex [0:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=0.0:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+0.0/TB[0v];[1:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+5.28/TB[1v];[2:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+10.56/TB[2v];[3:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+15.84/TB[3v];[4:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+21.12/TB[4v];[5:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+26.400000000000002/TB[5v];[6:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+31.68/TB[6v];[7:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+36.96/TB[7v];[8:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+42.24/TB[8v];[9:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=237.6,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=10.0:alpha=0,setpts=PTS-STARTPTS+47.52/TB[9v];[0v][1v]overlay[1v];[1v][2v]overlay[1v];[1v][3v]overlay[1v];[1v][4v]overlay[1v];[1v][5v]overlay[1v];[1v][6v]overlay[1v];[1v][7v]overlay[1v];[1v][8v]overlay[1v];[1v][9v]overlay -y /Users/user/src/python/VideoMaker2/output/videos/1547957911138.mp4
And the resulting video's duration ends up as 57 seconds (3 seconds difference) for some reason. If I create a longer video, the difference will grow proportionally.
But if I create a video with same parameters but at 60 FPS, it's OK:
/usr/local/bin/ffmpeg -i /Users/user/src/python/VideoMaker2/input/images/test/1.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/2.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/3.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/4.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/5.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/6.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/7.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/8.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/9.jpg -i /Users/user/src/python/VideoMaker2/input/images/test/10.jpg -r 60 -t 60 -vcodec libx264 -preset ultrafast -tune zerolatency -pix_fmt yuv420p -filter_complex [0:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=0.0:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+0.0/TB[0v];[1:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+5.28/TB[1v];[2:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+10.56/TB[2v];[3:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+15.84/TB[3v];[4:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+21.12/TB[4v];[5:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+26.400000000000002/TB[5v];[6:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+31.68/TB[6v];[7:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+36.96/TB[7v];[8:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=0.6600000000000001:alpha=0,setpts=PTS-STARTPTS+42.24/TB[8v];[9:v]format=yuv420p,format=yuv420p,scale=trunc(min(iw*2880/ih\,5120)/2)*2:-2,pad=5120:2880:(5120-iw)/2:(2880-ih)/2:color=black,zoompan=z='zoom+0.002':x='iw/2-(iw/zoom/2)':y='ih/2-(ih/zoom/2)':s=5120x2880:d=475.2,scale=trunc(min(iw*720/ih\,1280)/2)*2:-2,fade=t=in:st=0:d=1.3200000000000003:alpha=1,fade=t=out:st=7.920000000000001:d=10.0:alpha=0,setpts=PTS-STARTPTS+47.52/TB[9v];[0v][1v]overlay[1v];[1v][2v]overlay[1v];[1v][3v]overlay[1v];[1v][4v]overlay[1v];[1v][5v]overlay[1v];[1v][6v]overlay[1v];[1v][7v]overlay[1v];[1v][8v]overlay[1v];[1v][9v]overlay -y /Users/user/src/python/VideoMaker2/output/videos/1547958267849.mp4
Can someone please say where the mistake is in this command?
Upd. Class that is responsible for filter creation:
class KenBurnsCreator(object):
HALF_TRANSITION_RATIO = 0.1
__width: float
__height: float
__images: List[str]
__duration: float
__frame_rate: int
__half_transition_duration: float
__animation_duration: float
__logger = get_logger(__qualname__)
def __init__(self, width: float, height: float, images: List[str], duration: float, frame_rate: int) -> None:
super().__init__()
self.__width = width
self.__height = height
self.__images = images
self.__duration = duration
self.__frame_rate = frame_rate
self.__animation_duration = duration / float(len(self.__images)) * (1 + self.HALF_TRANSITION_RATIO)
self.__half_transition_duration = self.__animation_duration * self.HALF_TRANSITION_RATIO
self.__logger.debug(f'Animation duration: {self.__animation_duration}, half transition duration: {self.__half_transition_duration}')
def __create_ken_burns_translation_filter(self) -> str:
upscale_ratio = max(3, int(3000 / self.__height))
w = int(self.__ceil(self.__width * upscale_ratio))
h = int(self.__ceil(self.__height * upscale_ratio))
translation_duration = self.__frame_rate * (self.__animation_duration + self.__half_transition_duration * 2)
filter_str = 'format=yuv420p'
filter_str += ','
filter_str += f'scale=trunc(min(iw*{h}/ih\\,{w})/2)*2:-2'
filter_str += ','
filter_str += f'pad={w}:{h}:'
filter_str += f'({w}-iw)/2:'
filter_str += f'({h}-ih)/2:'
filter_str += f'color=black'
filter_str += ','
filter_str += 'zoompan='
filter_str += 'z=\'zoom+0.002\':'
filter_str += 'x=\'iw/2-(iw/zoom/2)\':'
filter_str += 'y=\'ih/2-(ih/zoom/2)\':'
filter_str += f's={w}x{h}:'
filter_str += f'd={translation_duration:.1f}'
return filter_str
def __stitch(self, count: int) -> str:
filter_str = '[0v][1v]'
filter_str += 'overlay'
for i in range(2, count):
filter_str += '[1v];'
filter_str += '[1v]'
filter_str += f'[{i}v]'
filter_str += 'overlay'
return filter_str
def __create_filter_content_for_ken_burns(self, count: int, index: int, animation: str) -> str:
fade_duration_1 = 0.0 if index == 0 else self.__half_transition_duration * 2.0
fade_start = self.__animation_duration + self.__half_transition_duration * 2.0
fade_duration_2 = 10.0 if index == count - 1 else self.__half_transition_duration
pts = (self.__animation_duration - self.__half_transition_duration * 2.0) * float(index)
filter_str = f'[{index}:v]'
filter_str += 'format=yuv420p'
filter_str += ','
filter_str += animation
filter_str += ','
filter_str += 'scale='
filter_str += f'trunc(min(iw*{int(self.__height)}/ih\\,{int(self.__width)})/2)*2:-2'
filter_str += ','
filter_str += 'fade=t=in:st=0:'
filter_str += f'd={fade_duration_1}:'
filter_str += 'alpha=1'
filter_str += ','
filter_str += 'fade=t=out:'
filter_str += f'st={fade_start}:'
filter_str += f'd={fade_duration_2}:'
filter_str += 'alpha=0'
filter_str += ','
filter_str += f'setpts=PTS-STARTPTS+{pts}/TB'
filter_str += f'[{index}v];'
return filter_str
# ceil and round to 2-divisible
def __ceil(self, number: float):
new = math.ceil(number)
if new % 2 != 0:
new += 1
return new
def create_animation_filter(self) -> str:
filter_str = ''
images_count = len(self.__images)
for index in range(images_count):
ken_burns_translation_filter = self.__create_ken_burns_translation_filter()
content = self.__create_filter_content_for_ken_burns(images_count, index, ken_burns_translation_filter)
filter_str += content
filter_str += self.__stitch(images_count)
return filter_str
