Ever get frustrated that AI video models can’t have characters speak and act in the same clip? You either get a silent movie or a static avatar. It’s a huge pain.
Well, I just saw an incredible post from Tianyu Xu, and he’s figured out how to crack this with Veo 3!
He discovered that Veo 3 can do both, show AND tell, in a single generation. This is a total game-changer for storytelling and educational content. I was blown away when I saw his results.
According to his tests, he was able to get most effects to work by following 5 simple rules. You have to see this trick he shared!
✨ Tianyu Xu’s 5 Rules for Prompting Veo 3: ✨
- 📌 One Job at a Time: Don’t ask the AI to multitask in a single prompt. Keep it focused.
- ✍️ Keep it Simple: Describe the effects or actions you want in plain, clear English. No need for fancy jargon.
- 🖼️ Image is King: Double down on describing the image you want. The video part will follow.
- 🚀 Embrace Imperfection: Don’t aim for a perfect final clip. Use the good parts and iterate.
- 💡 Know Your Tools: Remember that Veo 3 is amazing for this ‘show and tell’ style, but other models might be better for super wild, crazy effects.
Tianyu Xu found it’s an ideal model for this kind of content, and anyone can get the hang of it with his advice.
This is just my quick summary of his awesome discovery. For the full breakdown and all the details, go check out the original post by Tianyu Xu!