If you could eliminate discomfort, would you?
Wouldn’t eliminating discomfort be eliminating the ability to discern what i do not like?
And therefore eliminating the ability to discern what i do like?
And therefore eliminating the ability to discern myself?
And therefore eliminating the ability to discern who i am and what makes of me so?
If i could eliminate discomfort, I would not.
While some of the attention is clearly just a hype wave, generative AI models end up being a great solution to the storyboarding use-case for a number of reasons:
Generative techniques enable infinite experimentation at the cost of a model call. If you can get shots in seconds instead of days, video creatives are able to explore their visions more freely.
These models are visually expressive and rich in ways we've never seen before from artificial systems, enabling artists to follow their creative whimsy in new ways.
Because these models can learn from data, they continuously improve and adapt as they are used more. This allows for learned personalization of an artists' style and brand, something that existing storyboarding solutions cannot do.
Storyboarding is a fault-tolerant problem for generative models to be applied to. In other words, while it's clear that generative systems aren't perfect today, the storyboarding use-case tolerates occasional hiccups such as distorted faces or additional limbs. This means generative AI can provide benefits to the storyboarding workflow today.
The power of AI is not creativity, but scale. Real stories can only be written by real humans. Delivering and amplifying them is where AI can complement us. You pour your soul into writing a screenplay, @StoriaAI puts its GPU cycles into illustrating it in 1000 ways.
4:36 PM · May 11, 2023
I was asked to come talk about "AI art" this Thursday in front of a small selected group of individuals who were curious about the development of the field over the last few months. Naturally I wanted to blow a few minds – in which I succeeded. Here's what I showed them
First course on the menu? Good ol' regular text-to-image which was basically my gateway drug into AI art in July 2022. The first image I've ever created reinvoked that magic I felt as a kid, where magic still was subjectively real.
We've seen an insane acceleration in image quality generated in the last 9 months. So how to better kickoff this thing by questioning reality itself. Can you tell which one of these images is real? Answer below
Answer: None of them. Sorry, I tricked you Both images were actually created with Midjourney v5.1 – the latest State of the Art image model there is at the time of writing this: https://midjourney.com Food for thought: How can people recognize if an image is real?
Just as a comparison. This is how things looked back in July 2022 when I joined and the v2 model was considered State of the Art. The below images have been created with the same prompts for comparison.
7:51 AM · May 26, 2023
Soaking up the “clean light” of the desert sun, Robert Yeoman’s camera reveals most of these sights to us in the span of a single 360-degree swivel, a flex that underlines Anderson’s absolute command over the film’s Chinchón set where his characters will soon be trapped against their will, thus forcing them to surrender the delusion of control that has defined so many of Anderson’s characters over the course of his career. It’s maybe the most radical thing that has ever happened in one of his movies — the sort of transformative moment that A.I. could never dream up no matter how much data it ingested — and it spins “Asteroid City” in a cosmic new direction. What until then was just another immaculate Wes Anderson film suddenly becomes one of a kind.