You joined this community because you want to create better AI videos. But the real question is… why? Are you trying to grow your business? Do you want to build an audience and make money on social media? Are you hoping to create ads or content for brands? Do you want to launch an AI influencer, (Like me!🥰)? Do you want to tell stories, make films, or finally bring the weird ideas in your head to life? Or is this simply a creative outlet—something fun that lets you experiment, learn, and make cool stuff? There’s no wrong answer. I’m genuinely curious about what brought you here and what you’re hoping AI content creation can help you accomplish. @Scotty Art has generated millions of dollars online over years. The more we know, the better we can help you get there! Drop your answer below. Be specific. Why are you here—and what would success look like for you? 👇

Hey everyone — new guy here. Thanks for having me! I’ve been following what Scotty has been doing with Keira and some of the other AI characters, and the realism is what really caught my attention. The first time I saw @Keira K , I genuinely thought she was a real person. I’m working on a project where we’re considering creating two recurring virtual hosts — one male and one female — and the quality requirement is very high. They need to look and move convincingly enough that they don’t immediately read as AI, while still being clearly disclosed as virtual/AI hosts. I have a few questions about whether ShortPulse could handle the workflow we have in mind: 1. Is Keira’s current talking-video workflow created primarily or entirely inside ShortPulse? If so, which model/workflow is being used for her facial animation, lip-sync, movement, and overall realism? 2. Can ShortPulse use a downloaded NotebookLM Audio Overview as the audio source? Specifically, NotebookLM can generate a conversation between two speakers. Could we take that two-person audio and use it with two persistent ShortPulse characters? 3. If we have one male character and one female character, can ShortPulse automatically distinguish the two speakers in the audio and assign Speaker A to one character and Speaker B to the other, with each character only speaking their own lines? 4. If it cannot do that automatically, what would be the best ShortPulse workflow? Would we need to separate the two speakers into individual audio tracks first and generate each character separately? 5. Can the same two characters be kept truly consistent across many videos — same face, body, general appearance, voice, and identity — while changing clothing, locations, camera angles, etc.? 6. Can each character have a permanent reusable voice, so they sound like the same two people in every episode? 7. Can ShortPulse create a convincing two-person conversation visually, including alternating close-ups, two-shots, reactions while the other person is speaking, and natural facial/head/body movement? Or would the better approach be to generate each person separately and edit the conversation together afterward? 8. Finally, for people who have done this kind of recurring photorealistic-character work in ShortPulse, which models/workflows are currently giving the most realistic human results? Cost matters, but realism matters much more for this project.