OpenAI has lobotomized DALL-E to the point that it is virtually worthless for continuity. I doubt they've done much better for switching between scenes of motion pictures. You can't do such simple things as storyboards or graphic novels. The way they achieved this feat of engineering?
By closing off the only way of getting a face to be the same recognizable character between frames -- which is to specify it as a well-sampled celebrity. They yammer at you how this is some sort of violation. So what do you do to get it to render a face consistently between frames? You describe the character in detail and hope that it will do something reasonable. Here, for example, is what I was limited to doing for a storyboard I wanted to do: https://twitter.com/jabowery/status/1755378830426915008 <https://twitter.com/jabowery/status/1755378830426915008/photo/1> https://twitter.com/jabowery/status/1755382127510564904 ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4ad5d8c386d0e116-Mc34b9d32018972272eb7c796 Delivery options: https://agi.topicbox.com/groups/agi/subscription
