alt Hacker NewsI feel like there is a sweet spot for AI generation of images and videos that I would describe as "charmingly bad", like the stuff we got from the old CLIP+VQGAN models. I feel like Sora has jumped past that into the valley of "unappealingly bad".
I feel like there is a sweet spot for AI generation of images and videos that I would describe as "charmingly bad", like the stuff we got from the old CLIP+VQGAN models. I feel like Sora has jumped past that into the valley of "unappealingly bad".
I think that's why humor and memes are such good targets for this type of stuff. If you look up videos like "luma memes compilation," it takes well-known memes and distorts them in uncanny, freaky, and bizarre ways. Yet the fact the original subject is a meme somehow bypasses the uncanny valley repulsion. We seem to accept that much more readily, for whatever reason.