The Creative Mind: Combinatorial Mindset in AI

20/08/24 20:00 Filed in: Artificial Intelligence

Introduction

In the ever-evolving world of AI and creativity, having a combinatorial mindset is key to unlocking the full potential of AI technology in today’s world. Over the past few weeks, I’ve been immersed in research and my challenge project of creating a movie trailer for a friend’s book with AI. This journey has reinforced the importance of agility and need to combine various AI tools to achieve a goal of a polished multimodal end product.

The Creative Flowchart and AI Orchestration

Imagine a flowchart where the creative mind and the ideas sit at the core of the production. The packaged content(the book) is fed into a Custom GPT as the knowledge base for the source of truth. Here the custom GPT, acts as an interactive source of truth for the entire production. It becomes the central knowledge hub for communication and generation of content for instructing various AI tools and orchestrating the complex interplay between different elements of the project.

At this point as the AI Director, I guide the process, directing the tools and continuously assessing their outputs to ensure they meet the desired specifications. The custom GPT serves as a production assistant that knows everything about the content, generating prompts for various aspects and ensuring consistency throughout. From this central hub, different tools branch out to handle specific tasks:

Text: Tools like ChatGPT can be used to create summaries, scripts, character descriptions, media prompts, and storyboards
Sound: Music, sound effects, and voiceovers are crafted using AI-driven sound design tools (Udio, WellSaidLabs, Elevenlabs), bringing auditory depth to the trailer.
Image: Tools like DALL·E and MidJourney are used to create detailed character and background images.
Video: Animation and motion are added using tools like Luma Dream Machine, RunwayML, Sora, Vero and Kling, where characters come to life against dynamic backdrops.

Integration: The Art of Combining AI Outputs

The true art lies in integrating these diverse outputs. Each tool excels in a specific area, but it’s the combination of their strengths that brings the project to life. The Custom GPT helps to ensure consistency and coherence, making the whole greater than the sum of its parts.

Balancing AI and Traditional Tools

We’re currently in a transitional period from using traditional digital creative tools to AI-assisted tools. This means sometimes switching back to traditional methods when needed. For example, while AI tools have been instrumental in generating assets for this project, I have found using Photoshop and its AI features useful for manipulating background and character images. As of today I find it still to be a challenge to assemble all assets via AI, so I still find a traditional digital video editor with AI features the best way to assemble them effectively.

There is a race to create an all-encompassing tool like LTX Studio, invideo, or the upcoming Morphic, but the currently available tools I’ve played with are not quite there yet. The race continues for the creative mind to find the right tool. In this transitional period, being open to combining different tools allows for more creativity and human control, enabling us to use these multimodal AI tools appropriately and creatively.

002-screenshot2

Conclusion: Creativity as Composition

Think of it like composing an orchestral soundtrack. The composer knows the theme and melodies but combines different timbres of musical instruments and dynamics to create a master final engaging product. Similarly, I believe today, the new AI Director/Artist - creative composer can combine various tools and technologies to add the subtle human aspects for bringing something unique to life.

Onward…Forward!

Check out the latest version of the challenge project AI trailer below. Please let me know if you have any questions or thoughts on any aspect of the production. A work in progress

Moving Beyond the Minds Eye Through AI

16/08/24 08:00 Filed in: AI for the Creatiive Mind

This blog post explores how new AI tools can be used to empower the Creative Minds to bring their ideas in the minds eye to life.