Frame-by-frame continuity with GPT Image 2.5 could beat video models for anime, author argues
The author argues AI anime should rely on image continuity models like GPT Image 2.5 rather than video models, and complains that its watermark stacks across chained generations and its color consistency is poor.
I think the future of AI-assisted anime is not video models, but image continuity models like GPT Image 2.5. Predicting the next frame conditioned on the previous frame gives you much better control than predicting the next few seconds of video. You also don't need to predict all 24 frames every second. Since anime is basically layered animation, you can keep the same image for 5seconds while only the hand is waving or the eyes are blinking. Frame by frame prediction is also the nature of 2D anime. I've never really get the idea with turning everything into ultra-smooth 60 FPS animation. The problem with this model right now is that the 'invisible watermark' is too visible, which is really annoying. When you do chained generations, the watermark keeps stacking up to the point where it actually makes the project worse. It also has very poor color consistency.