Earlier quoted context omitted.
Assuming that's your project, the GitHub link from the PyPi page is a 404.
It's live now, https://github.com/vlm-run/mm .
Awesome!
Claude-real-video － any LLM can watch a video
81–86 of 86 posts
Re: Claude-real-video － any LLM can watch a video
#82Interesting, but how expensive does it get?
[flagged]
Re: Claude-real-video － any LLM can watch a video
#83my experience with ffmpeg scene detection is that it's flaky. it works, sometimes, but not reliable by any means
[flagged]
Re: Claude-real-video － any LLM can watch a video
#84So this work basically by dividing into frames..
[flagged]
Re: Claude-real-video － any LLM can watch a video
#85Earlier quoted context omitted.
Really, does this work now? What about NotebookLM? I was using it a lot until i realised it was only analysing the transcripts and not the video because i was mostly using it for technical ones with important charts.
It can tell you what’s on the screen at given point in time. My pipeline is mostly around simple questions like “does this video contain cars?” Not sure if it can spot charts on screen.
mm can spot charts on a screen. did you try it?
Re: Claude-real-video － any LLM can watch a video
#86I was creating a scene by scene remake of a cutscene from an old DOS game. The sprite sheet had several sprites which were cycled (e.g. a horse with it's head down and up). The engine would cycle through these regularly to create some "liveliness" in the background. It was tedious and I didn't want to figure out which sprites belonged at which pixel location. I recorded a video of the relevant part of the cutscene us…
Ask a coding agent to decode the assets. Works pretty often for such old games.