Peculiarities of Working on “Für Lili”
I’ve already shared some thoughts on working with video generators and the difficulty of controlling their output through prompts. Even when you feed the generator the exact dialogue, characters often overact, introducing unwanted emotion and unnecessary gestures.
Another limitation is that the generated clips are very short — typically around five seconds — which is rarely enough to cover the timing of narration or dialogue. As a result, instead of fully staging a scene, you often end up suggesting it.
There was also an additional challenge specific to this project. The story is built around Beethoven’s Bagatelle “Für Elise,” so I had to balance two layers at once: the narrative describing the music and its effect on the characters, and the music itself, which also needs to affect the viewer.
I’m interested in whether that balance comes through — and where it breaks.
I’ve watched the film. The story itself is actually quite good; I can well imagine the older lady’s irritation. A song like that, which is never played to the end, drives you mad.
I’m not entirely sure what exactly you’re asking, but this is what struck me. The dubbing isn’t in sync with the characters’ mouths, and I personally find that distracting. I have to try very hard to ignore it. The narrator also speaks too quickly, so it doesn’t match the visuals. Perhaps having all the dialogue start a few beats later might solve this problem.
Incidentally, I don’t think the voices really suit the characters either.
Perhaps @bambuka can help you further?
Could you please use the hashtag #artonsteemit first?
🍀❤️
@wakeupkitty