Opus 5.5 music video for p(doom) needed prompts to avoid repeated imagery
The author made a p(doom) music video with Opus 5.5 and found the model kept reusing the same few images, requiring prompts to exclude them, while noting clear gains in computer use and taste.
Yet another Opus 5.5 p(doom) music video I noticed a lot of the other ones I'd seen for this song had the same imagery, and I assumed they were all using one as a reference, but no, the model does just latch onto the same few ideas. I had to specifically prompt *not* to use some of those images The jump in computer use (and "taste") is really quite impressive. I'm not a fan of AI for art but there's obviously a huge market for it once the slop factor is gone (/ it's not recognisable as AI generated).