zlacker

[parent] [thread] 9 comments
1. Habgdn+(OP)[view] [source] 2025-12-06 05:42:20
An amateur tip that I sometimes use after I reencode something to check what i lost:

ffmpeg -i source.mkv -i suspect.mkv -filter_complex "blend=all_mode=difference" diff_output.mkv

I saw these claims before but still have not found someone to show a diff or post the source for comparison. It would be interesting.

replies(3): >>rpastu+3g >>jbaber+sg >>randoo+Cp
2. rpastu+3g[view] [source] 2025-12-06 09:52:23
>>Habgdn+(OP)
Hehe, I occasionally use a similar approach for visual regression testing: https://untested.sonnet.io/notes/visual-snapshot-tests-cheap...
3. jbaber+sg[view] [source] 2025-12-06 09:57:25
>>Habgdn+(OP)
Thank you for this good idea and oneliner.
4. randoo+Cp[view] [source] 2025-12-06 11:55:11
>>Habgdn+(OP)
Jill Bearup posted a video about this a while ago, showing a short and the original side by side: https://www.youtube.com/watch?v=kd692naF-Cc (note the short is shown at 0:31)

Edit: The changes made by the ai are a lot more vissible in the higher quality video uploaded to patreon: https://www.patreon.com/posts/136994036 (this was also linked in the pinned comment on the youtube video)

replies(4): >>sgeren+Cy >>AnonHP+1V >>tetris+hY >>IshKeb+LB1
◧◩
5. sgeren+Cy[view] [source] [discussion] 2025-12-06 13:24:56
>>randoo+Cp
The before/after on this just looks like compression artifacts/smoothing to me.
◧◩
6. AnonHP+1V[view] [source] [discussion] 2025-12-06 16:31:19
>>randoo+Cp
It must be my eyes and the small screen on my phone. I couldn’t find any differences in the video on Patreon, which was annoying enough to watch with the actual comparison clip being just a couple of seconds or so, and I had to rewind and check again. I wish it had shown more of the comparisons. Most of the current video was just commentary.
replies(1): >>gblarg+xa2
◧◩
7. tetris+hY[view] [source] [discussion] 2025-12-06 16:58:06
>>randoo+Cp
I still can't see the differences in the patreon
replies(1): >>sgeren+rZ
◧◩◪
8. sgeren+rZ[view] [source] [discussion] 2025-12-06 17:08:09
>>tetris+hY
It’s because you’re looking for some kind of “smoking gun” AI transformation. In reality it just looks like the YouTube one is more compressed and slightly blurred. Some people are apparently just learning that YouTube recompresses videos.
◧◩
9. IshKeb+LB1[view] [source] [discussion] 2025-12-06 22:37:24
>>randoo+Cp
Yeah I also can't see the difference on the high quality video. I am on my phone though tbf.

Also, minus 100 points to Jill for being happy about being able to use AI to automatically edit out all the silence from her videos. That's far more annoying than any barely perceptible visual artifacts.

Why do people think wall-of-text videos are good?

◧◩◪
10. gblarg+xa2[view] [source] [discussion] 2025-12-07 05:26:20
>>AnonHP+1V
Same here, on a big screen, I don't see anything notable. I really hope this isn't a mass delusion because YouTube started applying a sharpness ("edge enhancement") filter to videos to make them look sharper. It sure looks like that to me, because I hate this filter and how so many movie transfers have it added, with the ringing at the edges this filter leaves.
[go to top]