Hey Folks! I am working on project where a client requested images be generated with Nano Banana via Gemini. The reasoning, the images seem to have more detail. As I started working with the project, I noticed Gemni having issues with prompts that "worked" in ChatGPT: 1. Using 3 character reference sheets and a background image. 2. Repeating image reference prompts failed Note: I was working inside a NotebookLLM. I switched to a new chat outside of my Notebook, and still experienced issues. Maybe I need to spend more time learning how to prompt in Gemini, because no LLM is the same.

Hey Folks! I gave a LIVE presentation on "Google Flow 3.1 Fundaments" with @Nick Nebelsky today, over in his AI STORYTELLERS community. During the presentation, we tried to use the functionality of "inserting" objects into a video.. it didn't work at the time, so I tried again afterwards: The baby dragon was added in the edit mode of Google Flow with a prompt of: "add a purple dragon dancing"

Hey Folks! Consistency is the foundation. You learn how to build it up, keep it and then you're off to the races! At some point in your journey of creating Consistent Character images/Visual Story Images you'll learn "AI workflows" that help facilitate their creation. I've done that numerous times, with my guides, and I'll most likely share more, simply because there are many ways to get to a solution. I can now create short visual story videos within 60 minutes, barring any issues. What are you creating today?

Hey Folks! Level 3 has a new class module, Creating a Wig Model (Super Easy). This module demonstrates another (use case) for using the technique of "compositing". Play around with compositing, it may be one of the most under-utilized techniques for creating visual stories scenes.