TOOLS: ChatGPT & Gemini for Prompt development, VEO3 Text to Video, AfterEffects/Photoshop for cleanup, and Premiere as Editor.
This is an Ai Study proposed to me by a friend, a professor at NYU. It required a deep dive into Ai to recreate a real scenario; 4 characters at an office space, with a subject discussion, and a clear communication conflict, but the endgame is to figure out an Ai workflow, and how well can we direct and block based on the tools available.
The process and challenges.
To be fair, I should say, this was my first attempt at working with AI Video creation, and aside of ChatGPT, Perplexity, and Firefly, this is the first time I fully engaged Ai as the building block to substitute photography production. In the past, I have used Ai in Post-Production to create background extensions, patches, replacement elements, rather small tasks that could take some time to create. I never got perfection but I was able to use it successfully for the purpose intended.
It took me about 3 weeks on-and-off to wrap my head around prompting and learning to pivot from my results, and to get acquainted to the limitations. The amount of days in post boil down to about a week.
There was audio cleanup to be done, some picture inconsistencies that either were too little to worry about, in other cases I had to patch, reframe, cut out, color tone, etc... But at the end, the process served it's purpose.